fix(skill): restore load-bearing negations in post-approve-merger SKILL.md - #24
Merged
Merged
Conversation
…LL.md PR #23 had three negation-form directives rewritten as positive imperatives during the auto-reviewer pass, in a mistaken application of the BT-agent optimization-playbook S1 rule to a Hermes infrastructure skill. The S1/SD4 rules in sdlc-review have since been scoped BT-agent-only — but the rewrites in #23 landed before that scoping fix, so the load-bearing prohibitions are gone from the merged skill content. Restore them: 1. Auth: add explicit 'Never use sahilm-ti credentials' with the two concrete consequences (audit-trail misattribution + keychain prompt blocking the worker). The bare 'use sahilm-ai exclusively' positive form left the door open to drift, as evidenced by PR #23 itself — commit 7da3474 in that PR was authored as sahilm-ti. 2. Terminator contract: add explicit 'Do NOT call kanban_review' — without this prohibition the worker could re-loop the card through the auto-reviewer after Sahil has already approved, defeating the one-approval-equals-merged contract that motivated #23 in the first place. 3. Stop clause: 'After the single terminal call, stop — do not attempt any further gh/git/kanban_* operations.' A second terminal call corrupts the event log; the positive-only 'stop' form is too ambiguous (stop what? stop thinking? the model may interpret it as stop typing but keep tool-calling). No code changes. No test changes. Skill-content-only fix.
|
Warning Review limit reached
More reviews will be available in 21 minutes and 23 seconds. Learn how PR review limits work. Your organization has run out of usage credits. Purchase more in the billing tab. ⌛ How to resolve this issue?After more reviews become available, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans include higher PR review limits than trial, open-source, and free plans. In all cases, reviews become available again over time. During sustained high-volume PR review activity, CodeRabbit may temporarily slow when the next review becomes available. Please see our Fair Usage Limits Policy for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (1)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
sahilm-ti
added a commit
that referenced
this pull request
May 28, 2026
…LL.md (#24) PR #23 had three negation-form directives rewritten as positive imperatives during the auto-reviewer pass, in a mistaken application of the BT-agent optimization-playbook S1 rule to a Hermes infrastructure skill. The S1/SD4 rules in sdlc-review have since been scoped BT-agent-only — but the rewrites in #23 landed before that scoping fix, so the load-bearing prohibitions are gone from the merged skill content. Restore them: 1. Auth: add explicit 'Never use sahilm-ti credentials' with the two concrete consequences (audit-trail misattribution + keychain prompt blocking the worker). The bare 'use sahilm-ai exclusively' positive form left the door open to drift, as evidenced by PR #23 itself — commit 7da3474 in that PR was authored as sahilm-ti. 2. Terminator contract: add explicit 'Do NOT call kanban_review' — without this prohibition the worker could re-loop the card through the auto-reviewer after Sahil has already approved, defeating the one-approval-equals-merged contract that motivated #23 in the first place. 3. Stop clause: 'After the single terminal call, stop — do not attempt any further gh/git/kanban_* operations.' A second terminal call corrupts the event log; the positive-only 'stop' form is too ambiguous (stop what? stop thinking? the model may interpret it as stop typing but keep tool-calling). No code changes. No test changes. Skill-content-only fix. Co-authored-by: Sahil (AI) <266772320+sahilm-ai@users.noreply.github.com>
sahilm-ti
added a commit
that referenced
this pull request
May 28, 2026
…LL.md (#24) PR #23 had three negation-form directives rewritten as positive imperatives during the auto-reviewer pass, in a mistaken application of the BT-agent optimization-playbook S1 rule to a Hermes infrastructure skill. The S1/SD4 rules in sdlc-review have since been scoped BT-agent-only — but the rewrites in #23 landed before that scoping fix, so the load-bearing prohibitions are gone from the merged skill content. Restore them: 1. Auth: add explicit 'Never use sahilm-ti credentials' with the two concrete consequences (audit-trail misattribution + keychain prompt blocking the worker). The bare 'use sahilm-ai exclusively' positive form left the door open to drift, as evidenced by PR #23 itself — commit 7da3474 in that PR was authored as sahilm-ti. 2. Terminator contract: add explicit 'Do NOT call kanban_review' — without this prohibition the worker could re-loop the card through the auto-reviewer after Sahil has already approved, defeating the one-approval-equals-merged contract that motivated #23 in the first place. 3. Stop clause: 'After the single terminal call, stop — do not attempt any further gh/git/kanban_* operations.' A second terminal call corrupts the event log; the positive-only 'stop' form is too ambiguous (stop what? stop thinking? the model may interpret it as stop typing but keep tool-calling). No code changes. No test changes. Skill-content-only fix. Co-authored-by: Sahil (AI) <266772320+sahilm-ai@users.noreply.github.com>
sahilm-ti
added a commit
that referenced
this pull request
May 28, 2026
…LL.md (#24) PR #23 had three negation-form directives rewritten as positive imperatives during the auto-reviewer pass, in a mistaken application of the BT-agent optimization-playbook S1 rule to a Hermes infrastructure skill. The S1/SD4 rules in sdlc-review have since been scoped BT-agent-only — but the rewrites in #23 landed before that scoping fix, so the load-bearing prohibitions are gone from the merged skill content. Restore them: 1. Auth: add explicit 'Never use sahilm-ti credentials' with the two concrete consequences (audit-trail misattribution + keychain prompt blocking the worker). The bare 'use sahilm-ai exclusively' positive form left the door open to drift, as evidenced by PR #23 itself — commit 7da3474 in that PR was authored as sahilm-ti. 2. Terminator contract: add explicit 'Do NOT call kanban_review' — without this prohibition the worker could re-loop the card through the auto-reviewer after Sahil has already approved, defeating the one-approval-equals-merged contract that motivated #23 in the first place. 3. Stop clause: 'After the single terminal call, stop — do not attempt any further gh/git/kanban_* operations.' A second terminal call corrupts the event log; the positive-only 'stop' form is too ambiguous (stop what? stop thinking? the model may interpret it as stop typing but keep tool-calling). No code changes. No test changes. Skill-content-only fix. Co-authored-by: Sahil (AI) <266772320+sahilm-ai@users.noreply.github.com>
sahilm-ti
added a commit
that referenced
this pull request
May 29, 2026
…LL.md (#24) PR #23 had three negation-form directives rewritten as positive imperatives during the auto-reviewer pass, in a mistaken application of the BT-agent optimization-playbook S1 rule to a Hermes infrastructure skill. The S1/SD4 rules in sdlc-review have since been scoped BT-agent-only — but the rewrites in #23 landed before that scoping fix, so the load-bearing prohibitions are gone from the merged skill content. Restore them: 1. Auth: add explicit 'Never use sahilm-ti credentials' with the two concrete consequences (audit-trail misattribution + keychain prompt blocking the worker). The bare 'use sahilm-ai exclusively' positive form left the door open to drift, as evidenced by PR #23 itself — commit 7da3474 in that PR was authored as sahilm-ti. 2. Terminator contract: add explicit 'Do NOT call kanban_review' — without this prohibition the worker could re-loop the card through the auto-reviewer after Sahil has already approved, defeating the one-approval-equals-merged contract that motivated #23 in the first place. 3. Stop clause: 'After the single terminal call, stop — do not attempt any further gh/git/kanban_* operations.' A second terminal call corrupts the event log; the positive-only 'stop' form is too ambiguous (stop what? stop thinking? the model may interpret it as stop typing but keep tool-calling). No code changes. No test changes. Skill-content-only fix. Co-authored-by: Sahil (AI) <266772320+sahilm-ai@users.noreply.github.com>
sahilm-ti
added a commit
that referenced
this pull request
Jun 3, 2026
…LL.md (#24) PR #23 had three negation-form directives rewritten as positive imperatives during the auto-reviewer pass, in a mistaken application of the BT-agent optimization-playbook S1 rule to a Hermes infrastructure skill. The S1/SD4 rules in sdlc-review have since been scoped BT-agent-only — but the rewrites in #23 landed before that scoping fix, so the load-bearing prohibitions are gone from the merged skill content. Restore them: 1. Auth: add explicit 'Never use sahilm-ti credentials' with the two concrete consequences (audit-trail misattribution + keychain prompt blocking the worker). The bare 'use sahilm-ai exclusively' positive form left the door open to drift, as evidenced by PR #23 itself — commit 7da3474 in that PR was authored as sahilm-ti. 2. Terminator contract: add explicit 'Do NOT call kanban_review' — without this prohibition the worker could re-loop the card through the auto-reviewer after Sahil has already approved, defeating the one-approval-equals-merged contract that motivated #23 in the first place. 3. Stop clause: 'After the single terminal call, stop — do not attempt any further gh/git/kanban_* operations.' A second terminal call corrupts the event log; the positive-only 'stop' form is too ambiguous (stop what? stop thinking? the model may interpret it as stop typing but keep tool-calling). No code changes. No test changes. Skill-content-only fix. Co-authored-by: Sahil (AI) <266772320+sahilm-ai@users.noreply.github.com>
sahilm-ti
added a commit
that referenced
this pull request
Jun 5, 2026
…LL.md (#24) PR #23 had three negation-form directives rewritten as positive imperatives during the auto-reviewer pass, in a mistaken application of the BT-agent optimization-playbook S1 rule to a Hermes infrastructure skill. The S1/SD4 rules in sdlc-review have since been scoped BT-agent-only — but the rewrites in #23 landed before that scoping fix, so the load-bearing prohibitions are gone from the merged skill content. Restore them: 1. Auth: add explicit 'Never use sahilm-ti credentials' with the two concrete consequences (audit-trail misattribution + keychain prompt blocking the worker). The bare 'use sahilm-ai exclusively' positive form left the door open to drift, as evidenced by PR #23 itself — commit 7da3474 in that PR was authored as sahilm-ti. 2. Terminator contract: add explicit 'Do NOT call kanban_review' — without this prohibition the worker could re-loop the card through the auto-reviewer after Sahil has already approved, defeating the one-approval-equals-merged contract that motivated #23 in the first place. 3. Stop clause: 'After the single terminal call, stop — do not attempt any further gh/git/kanban_* operations.' A second terminal call corrupts the event log; the positive-only 'stop' form is too ambiguous (stop what? stop thinking? the model may interpret it as stop typing but keep tool-calling). No code changes. No test changes. Skill-content-only fix. Co-authored-by: Sahil (AI) <266772320+sahilm-ai@users.noreply.github.com>
sahilm-ti
added a commit
that referenced
this pull request
Jun 15, 2026
…LL.md (#24) PR #23 had three negation-form directives rewritten as positive imperatives during the auto-reviewer pass, in a mistaken application of the BT-agent optimization-playbook S1 rule to a Hermes infrastructure skill. The S1/SD4 rules in sdlc-review have since been scoped BT-agent-only — but the rewrites in #23 landed before that scoping fix, so the load-bearing prohibitions are gone from the merged skill content. Restore them: 1. Auth: add explicit 'Never use sahilm-ti credentials' with the two concrete consequences (audit-trail misattribution + keychain prompt blocking the worker). The bare 'use sahilm-ai exclusively' positive form left the door open to drift, as evidenced by PR #23 itself — commit 7da3474 in that PR was authored as sahilm-ti. 2. Terminator contract: add explicit 'Do NOT call kanban_review' — without this prohibition the worker could re-loop the card through the auto-reviewer after Sahil has already approved, defeating the one-approval-equals-merged contract that motivated #23 in the first place. 3. Stop clause: 'After the single terminal call, stop — do not attempt any further gh/git/kanban_* operations.' A second terminal call corrupts the event log; the positive-only 'stop' form is too ambiguous (stop what? stop thinking? the model may interpret it as stop typing but keep tool-calling). No code changes. No test changes. Skill-content-only fix. Co-authored-by: Sahil (AI) <266772320+sahilm-ai@users.noreply.github.com>
sahilm-ti
added a commit
that referenced
this pull request
Jun 17, 2026
…LL.md (#24) PR #23 had three negation-form directives rewritten as positive imperatives during the auto-reviewer pass, in a mistaken application of the BT-agent optimization-playbook S1 rule to a Hermes infrastructure skill. The S1/SD4 rules in sdlc-review have since been scoped BT-agent-only — but the rewrites in #23 landed before that scoping fix, so the load-bearing prohibitions are gone from the merged skill content. Restore them: 1. Auth: add explicit 'Never use sahilm-ti credentials' with the two concrete consequences (audit-trail misattribution + keychain prompt blocking the worker). The bare 'use sahilm-ai exclusively' positive form left the door open to drift, as evidenced by PR #23 itself — commit 7da3474 in that PR was authored as sahilm-ti. 2. Terminator contract: add explicit 'Do NOT call kanban_review' — without this prohibition the worker could re-loop the card through the auto-reviewer after Sahil has already approved, defeating the one-approval-equals-merged contract that motivated #23 in the first place. 3. Stop clause: 'After the single terminal call, stop — do not attempt any further gh/git/kanban_* operations.' A second terminal call corrupts the event log; the positive-only 'stop' form is too ambiguous (stop what? stop thinking? the model may interpret it as stop typing but keep tool-calling). No code changes. No test changes. Skill-content-only fix. Co-authored-by: Sahil (AI) <266772320+sahilm-ai@users.noreply.github.com>
sahilm-ti
added a commit
that referenced
this pull request
Jun 22, 2026
…LL.md (#24) PR #23 had three negation-form directives rewritten as positive imperatives during the auto-reviewer pass, in a mistaken application of the BT-agent optimization-playbook S1 rule to a Hermes infrastructure skill. The S1/SD4 rules in sdlc-review have since been scoped BT-agent-only — but the rewrites in #23 landed before that scoping fix, so the load-bearing prohibitions are gone from the merged skill content. Restore them: 1. Auth: add explicit 'Never use sahilm-ti credentials' with the two concrete consequences (audit-trail misattribution + keychain prompt blocking the worker). The bare 'use sahilm-ai exclusively' positive form left the door open to drift, as evidenced by PR #23 itself — commit 7da3474 in that PR was authored as sahilm-ti. 2. Terminator contract: add explicit 'Do NOT call kanban_review' — without this prohibition the worker could re-loop the card through the auto-reviewer after Sahil has already approved, defeating the one-approval-equals-merged contract that motivated #23 in the first place. 3. Stop clause: 'After the single terminal call, stop — do not attempt any further gh/git/kanban_* operations.' A second terminal call corrupts the event log; the positive-only 'stop' form is too ambiguous (stop what? stop thinking? the model may interpret it as stop typing but keep tool-calling). No code changes. No test changes. Skill-content-only fix. Co-authored-by: Sahil (AI) <266772320+sahilm-ai@users.noreply.github.com>
sahilm-ti
added a commit
that referenced
this pull request
Jul 3, 2026
…LL.md (#24) PR #23 had three negation-form directives rewritten as positive imperatives during the auto-reviewer pass, in a mistaken application of the BT-agent optimization-playbook S1 rule to a Hermes infrastructure skill. The S1/SD4 rules in sdlc-review have since been scoped BT-agent-only — but the rewrites in #23 landed before that scoping fix, so the load-bearing prohibitions are gone from the merged skill content. Restore them: 1. Auth: add explicit 'Never use sahilm-ti credentials' with the two concrete consequences (audit-trail misattribution + keychain prompt blocking the worker). The bare 'use sahilm-ai exclusively' positive form left the door open to drift, as evidenced by PR #23 itself — commit 7da3474 in that PR was authored as sahilm-ti. 2. Terminator contract: add explicit 'Do NOT call kanban_review' — without this prohibition the worker could re-loop the card through the auto-reviewer after Sahil has already approved, defeating the one-approval-equals-merged contract that motivated #23 in the first place. 3. Stop clause: 'After the single terminal call, stop — do not attempt any further gh/git/kanban_* operations.' A second terminal call corrupts the event log; the positive-only 'stop' form is too ambiguous (stop what? stop thinking? the model may interpret it as stop typing but keep tool-calling). No code changes. No test changes. Skill-content-only fix. Co-authored-by: Sahil (AI) <266772320+sahilm-ai@users.noreply.github.com>
sahilm-ti
added a commit
that referenced
this pull request
Jul 9, 2026
…LL.md (#24) PR #23 had three negation-form directives rewritten as positive imperatives during the auto-reviewer pass, in a mistaken application of the BT-agent optimization-playbook S1 rule to a Hermes infrastructure skill. The S1/SD4 rules in sdlc-review have since been scoped BT-agent-only — but the rewrites in #23 landed before that scoping fix, so the load-bearing prohibitions are gone from the merged skill content. Restore them: 1. Auth: add explicit 'Never use sahilm-ti credentials' with the two concrete consequences (audit-trail misattribution + keychain prompt blocking the worker). The bare 'use sahilm-ai exclusively' positive form left the door open to drift, as evidenced by PR #23 itself — commit 7da3474 in that PR was authored as sahilm-ti. 2. Terminator contract: add explicit 'Do NOT call kanban_review' — without this prohibition the worker could re-loop the card through the auto-reviewer after Sahil has already approved, defeating the one-approval-equals-merged contract that motivated #23 in the first place. 3. Stop clause: 'After the single terminal call, stop — do not attempt any further gh/git/kanban_* operations.' A second terminal call corrupts the event log; the positive-only 'stop' form is too ambiguous (stop what? stop thinking? the model may interpret it as stop typing but keep tool-calling). No code changes. No test changes. Skill-content-only fix. Co-authored-by: Sahil (AI) <266772320+sahilm-ai@users.noreply.github.com>
sahilm-ti
added a commit
that referenced
this pull request
Jul 10, 2026
…LL.md (#24) PR #23 had three negation-form directives rewritten as positive imperatives during the auto-reviewer pass, in a mistaken application of the BT-agent optimization-playbook S1 rule to a Hermes infrastructure skill. The S1/SD4 rules in sdlc-review have since been scoped BT-agent-only — but the rewrites in #23 landed before that scoping fix, so the load-bearing prohibitions are gone from the merged skill content. Restore them: 1. Auth: add explicit 'Never use sahilm-ti credentials' with the two concrete consequences (audit-trail misattribution + keychain prompt blocking the worker). The bare 'use sahilm-ai exclusively' positive form left the door open to drift, as evidenced by PR #23 itself — commit 7da3474 in that PR was authored as sahilm-ti. 2. Terminator contract: add explicit 'Do NOT call kanban_review' — without this prohibition the worker could re-loop the card through the auto-reviewer after Sahil has already approved, defeating the one-approval-equals-merged contract that motivated #23 in the first place. 3. Stop clause: 'After the single terminal call, stop — do not attempt any further gh/git/kanban_* operations.' A second terminal call corrupts the event log; the positive-only 'stop' form is too ambiguous (stop what? stop thinking? the model may interpret it as stop typing but keep tool-calling). No code changes. No test changes. Skill-content-only fix. Co-authored-by: Sahil (AI) <266772320+sahilm-ai@users.noreply.github.com>
sahilm-ti
added a commit
that referenced
this pull request
Jul 11, 2026
…LL.md (#24) PR #23 had three negation-form directives rewritten as positive imperatives during the auto-reviewer pass, in a mistaken application of the BT-agent optimization-playbook S1 rule to a Hermes infrastructure skill. The S1/SD4 rules in sdlc-review have since been scoped BT-agent-only — but the rewrites in #23 landed before that scoping fix, so the load-bearing prohibitions are gone from the merged skill content. Restore them: 1. Auth: add explicit 'Never use sahilm-ti credentials' with the two concrete consequences (audit-trail misattribution + keychain prompt blocking the worker). The bare 'use sahilm-ai exclusively' positive form left the door open to drift, as evidenced by PR #23 itself — commit 7da3474 in that PR was authored as sahilm-ti. 2. Terminator contract: add explicit 'Do NOT call kanban_review' — without this prohibition the worker could re-loop the card through the auto-reviewer after Sahil has already approved, defeating the one-approval-equals-merged contract that motivated #23 in the first place. 3. Stop clause: 'After the single terminal call, stop — do not attempt any further gh/git/kanban_* operations.' A second terminal call corrupts the event log; the positive-only 'stop' form is too ambiguous (stop what? stop thinking? the model may interpret it as stop typing but keep tool-calling). No code changes. No test changes. Skill-content-only fix. Co-authored-by: Sahil (AI) <266772320+sahilm-ai@users.noreply.github.com>
sahilm-ti
added a commit
that referenced
this pull request
Jul 13, 2026
…LL.md (#24) PR #23 had three negation-form directives rewritten as positive imperatives during the auto-reviewer pass, in a mistaken application of the BT-agent optimization-playbook S1 rule to a Hermes infrastructure skill. The S1/SD4 rules in sdlc-review have since been scoped BT-agent-only — but the rewrites in #23 landed before that scoping fix, so the load-bearing prohibitions are gone from the merged skill content. Restore them: 1. Auth: add explicit 'Never use sahilm-ti credentials' with the two concrete consequences (audit-trail misattribution + keychain prompt blocking the worker). The bare 'use sahilm-ai exclusively' positive form left the door open to drift, as evidenced by PR #23 itself — commit 7da3474 in that PR was authored as sahilm-ti. 2. Terminator contract: add explicit 'Do NOT call kanban_review' — without this prohibition the worker could re-loop the card through the auto-reviewer after Sahil has already approved, defeating the one-approval-equals-merged contract that motivated #23 in the first place. 3. Stop clause: 'After the single terminal call, stop — do not attempt any further gh/git/kanban_* operations.' A second terminal call corrupts the event log; the positive-only 'stop' form is too ambiguous (stop what? stop thinking? the model may interpret it as stop typing but keep tool-calling). No code changes. No test changes. Skill-content-only fix. Co-authored-by: Sahil (AI) <266772320+sahilm-ai@users.noreply.github.com>
sahilm-ti
added a commit
that referenced
this pull request
Jul 15, 2026
…LL.md (#24) PR #23 had three negation-form directives rewritten as positive imperatives during the auto-reviewer pass, in a mistaken application of the BT-agent optimization-playbook S1 rule to a Hermes infrastructure skill. The S1/SD4 rules in sdlc-review have since been scoped BT-agent-only — but the rewrites in #23 landed before that scoping fix, so the load-bearing prohibitions are gone from the merged skill content. Restore them: 1. Auth: add explicit 'Never use sahilm-ti credentials' with the two concrete consequences (audit-trail misattribution + keychain prompt blocking the worker). The bare 'use sahilm-ai exclusively' positive form left the door open to drift, as evidenced by PR #23 itself — commit 7da3474 in that PR was authored as sahilm-ti. 2. Terminator contract: add explicit 'Do NOT call kanban_review' — without this prohibition the worker could re-loop the card through the auto-reviewer after Sahil has already approved, defeating the one-approval-equals-merged contract that motivated #23 in the first place. 3. Stop clause: 'After the single terminal call, stop — do not attempt any further gh/git/kanban_* operations.' A second terminal call corrupts the event log; the positive-only 'stop' form is too ambiguous (stop what? stop thinking? the model may interpret it as stop typing but keep tool-calling). No code changes. No test changes. Skill-content-only fix. Co-authored-by: Sahil (AI) <266772320+sahilm-ai@users.noreply.github.com>
sahilm-ti
added a commit
that referenced
this pull request
Jul 17, 2026
…LL.md (#24) PR #23 had three negation-form directives rewritten as positive imperatives during the auto-reviewer pass, in a mistaken application of the BT-agent optimization-playbook S1 rule to a Hermes infrastructure skill. The S1/SD4 rules in sdlc-review have since been scoped BT-agent-only — but the rewrites in #23 landed before that scoping fix, so the load-bearing prohibitions are gone from the merged skill content. Restore them: 1. Auth: add explicit 'Never use sahilm-ti credentials' with the two concrete consequences (audit-trail misattribution + keychain prompt blocking the worker). The bare 'use sahilm-ai exclusively' positive form left the door open to drift, as evidenced by PR #23 itself — commit 7da3474 in that PR was authored as sahilm-ti. 2. Terminator contract: add explicit 'Do NOT call kanban_review' — without this prohibition the worker could re-loop the card through the auto-reviewer after Sahil has already approved, defeating the one-approval-equals-merged contract that motivated #23 in the first place. 3. Stop clause: 'After the single terminal call, stop — do not attempt any further gh/git/kanban_* operations.' A second terminal call corrupts the event log; the positive-only 'stop' form is too ambiguous (stop what? stop thinking? the model may interpret it as stop typing but keep tool-calling). No code changes. No test changes. Skill-content-only fix. Co-authored-by: Sahil (AI) <266772320+sahilm-ai@users.noreply.github.com>
sahilm-ti
added a commit
that referenced
this pull request
Jul 21, 2026
…LL.md (#24) PR #23 had three negation-form directives rewritten as positive imperatives during the auto-reviewer pass, in a mistaken application of the BT-agent optimization-playbook S1 rule to a Hermes infrastructure skill. The S1/SD4 rules in sdlc-review have since been scoped BT-agent-only — but the rewrites in #23 landed before that scoping fix, so the load-bearing prohibitions are gone from the merged skill content. Restore them: 1. Auth: add explicit 'Never use sahilm-ti credentials' with the two concrete consequences (audit-trail misattribution + keychain prompt blocking the worker). The bare 'use sahilm-ai exclusively' positive form left the door open to drift, as evidenced by PR #23 itself — commit 7da3474 in that PR was authored as sahilm-ti. 2. Terminator contract: add explicit 'Do NOT call kanban_review' — without this prohibition the worker could re-loop the card through the auto-reviewer after Sahil has already approved, defeating the one-approval-equals-merged contract that motivated #23 in the first place. 3. Stop clause: 'After the single terminal call, stop — do not attempt any further gh/git/kanban_* operations.' A second terminal call corrupts the event log; the positive-only 'stop' form is too ambiguous (stop what? stop thinking? the model may interpret it as stop typing but keep tool-calling). No code changes. No test changes. Skill-content-only fix. Co-authored-by: Sahil (AI) <266772320+sahilm-ai@users.noreply.github.com>
sahilm-ti
added a commit
that referenced
this pull request
Jul 23, 2026
…LL.md (#24) PR #23 had three negation-form directives rewritten as positive imperatives during the auto-reviewer pass, in a mistaken application of the BT-agent optimization-playbook S1 rule to a Hermes infrastructure skill. The S1/SD4 rules in sdlc-review have since been scoped BT-agent-only — but the rewrites in #23 landed before that scoping fix, so the load-bearing prohibitions are gone from the merged skill content. Restore them: 1. Auth: add explicit 'Never use sahilm-ti credentials' with the two concrete consequences (audit-trail misattribution + keychain prompt blocking the worker). The bare 'use sahilm-ai exclusively' positive form left the door open to drift, as evidenced by PR #23 itself — commit 7da3474 in that PR was authored as sahilm-ti. 2. Terminator contract: add explicit 'Do NOT call kanban_review' — without this prohibition the worker could re-loop the card through the auto-reviewer after Sahil has already approved, defeating the one-approval-equals-merged contract that motivated #23 in the first place. 3. Stop clause: 'After the single terminal call, stop — do not attempt any further gh/git/kanban_* operations.' A second terminal call corrupts the event log; the positive-only 'stop' form is too ambiguous (stop what? stop thinking? the model may interpret it as stop typing but keep tool-calling). No code changes. No test changes. Skill-content-only fix. Co-authored-by: Sahil (AI) <266772320+sahilm-ai@users.noreply.github.com>
sahilm-ti
added a commit
that referenced
this pull request
Jul 28, 2026
…LL.md (#24) PR #23 had three negation-form directives rewritten as positive imperatives during the auto-reviewer pass, in a mistaken application of the BT-agent optimization-playbook S1 rule to a Hermes infrastructure skill. The S1/SD4 rules in sdlc-review have since been scoped BT-agent-only — but the rewrites in #23 landed before that scoping fix, so the load-bearing prohibitions are gone from the merged skill content. Restore them: 1. Auth: add explicit 'Never use sahilm-ti credentials' with the two concrete consequences (audit-trail misattribution + keychain prompt blocking the worker). The bare 'use sahilm-ai exclusively' positive form left the door open to drift, as evidenced by PR #23 itself — commit 7da3474 in that PR was authored as sahilm-ti. 2. Terminator contract: add explicit 'Do NOT call kanban_review' — without this prohibition the worker could re-loop the card through the auto-reviewer after Sahil has already approved, defeating the one-approval-equals-merged contract that motivated #23 in the first place. 3. Stop clause: 'After the single terminal call, stop — do not attempt any further gh/git/kanban_* operations.' A second terminal call corrupts the event log; the positive-only 'stop' form is too ambiguous (stop what? stop thinking? the model may interpret it as stop typing but keep tool-calling). No code changes. No test changes. Skill-content-only fix. Co-authored-by: Sahil (AI) <266772320+sahilm-ai@users.noreply.github.com>
sahilm-ti
added a commit
that referenced
this pull request
Aug 24, 2026
…LL.md (#24) PR #23 had three negation-form directives rewritten as positive imperatives during the auto-reviewer pass, in a mistaken application of the BT-agent optimization-playbook S1 rule to a Hermes infrastructure skill. The S1/SD4 rules in sdlc-review have since been scoped BT-agent-only — but the rewrites in #23 landed before that scoping fix, so the load-bearing prohibitions are gone from the merged skill content. Restore them: 1. Auth: add explicit 'Never use sahilm-ti credentials' with the two concrete consequences (audit-trail misattribution + keychain prompt blocking the worker). The bare 'use sahilm-ai exclusively' positive form left the door open to drift, as evidenced by PR #23 itself — commit 7da3474 in that PR was authored as sahilm-ti. 2. Terminator contract: add explicit 'Do NOT call kanban_review' — without this prohibition the worker could re-loop the card through the auto-reviewer after Sahil has already approved, defeating the one-approval-equals-merged contract that motivated #23 in the first place. 3. Stop clause: 'After the single terminal call, stop — do not attempt any further gh/git/kanban_* operations.' A second terminal call corrupts the event log; the positive-only 'stop' form is too ambiguous (stop what? stop thinking? the model may interpret it as stop typing but keep tool-calling). No code changes. No test changes. Skill-content-only fix. Co-authored-by: Sahil (AI) <266772320+sahilm-ai@users.noreply.github.com>
sahilm-ti
added a commit
that referenced
this pull request
Sep 2, 2026
…LL.md (#24) PR #23 had three negation-form directives rewritten as positive imperatives during the auto-reviewer pass, in a mistaken application of the BT-agent optimization-playbook S1 rule to a Hermes infrastructure skill. The S1/SD4 rules in sdlc-review have since been scoped BT-agent-only — but the rewrites in #23 landed before that scoping fix, so the load-bearing prohibitions are gone from the merged skill content. Restore them: 1. Auth: add explicit 'Never use sahilm-ti credentials' with the two concrete consequences (audit-trail misattribution + keychain prompt blocking the worker). The bare 'use sahilm-ai exclusively' positive form left the door open to drift, as evidenced by PR #23 itself — commit 7da3474 in that PR was authored as sahilm-ti. 2. Terminator contract: add explicit 'Do NOT call kanban_review' — without this prohibition the worker could re-loop the card through the auto-reviewer after Sahil has already approved, defeating the one-approval-equals-merged contract that motivated #23 in the first place. 3. Stop clause: 'After the single terminal call, stop — do not attempt any further gh/git/kanban_* operations.' A second terminal call corrupts the event log; the positive-only 'stop' form is too ambiguous (stop what? stop thinking? the model may interpret it as stop typing but keep tool-calling). No code changes. No test changes. Skill-content-only fix. Co-authored-by: Sahil (AI) <266772320+sahilm-ai@users.noreply.github.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Why
PR #23 had three negation-form directives in
skills/devops/post-approve-merger/SKILL.mdrewritten as positive imperatives during the auto-reviewer pass — a mistaken application of the BT-agent optimization-playbook S1 rule to a Hermes infrastructure skill. The S1/SD4 rules insdlc-reviewhave since been scoped BT-agent-only (commit0b28a85inhermes-config), but the rewrites in #23 landed before that scoping fix, so the load-bearing prohibitions are gone from the merged skill.What
Restore the three prohibitions:
Never use sahilm-ti credentialsin the auth section — with the two concrete consequences (audit-trail misattribution + macOS keychain prompts blocking the worker silently). The bare positive 'use sahilm-ai exclusively' wasn't sufficient: PR feat(kanban): post-approve merger agent #23's own commit7da3474181was authored assahilm-ti(the bot identity drift this skill was meant to prevent).Do NOT call kanban_reviewin the terminator contract — without this the worker could re-loop the card through the auto-reviewer after Sahil has already approved, defeating the one-approval-equals-merged contract that motivated feat(kanban): post-approve merger agent #23 in the first place.do not attempt any further gh/git/kanban_* operationsin the stop clause — the positive-only 'stop' was ambiguous (stop what? stop thinking?). A second terminal call after the terminator corrupts the event log.Why not just rewrite as positives again
Because each directive is a prohibition on a thing the model is otherwise inclined to do. The pink-elephant rule (which is BT-agent-playbook-only) says LLMs sometimes do the thing they're told not to. The opposite failure mode — which dominates in Hermes-infrastructure skills like this one — is the model interpreting a positive imperative as 'do X, and also a few other things that seem helpful'. Hermes workers run autonomously and durably; we need hard fences, not aspirational descriptions.
Risk
None. Skill-content-only. No code, no tests touched.
Related
hermes-configcommit0b28a85— scoped S1/SD4 BT-agent-only so this category of false-positive rejection cannot recur.