Conversation
…ttribution per copilot-instructions.md 305-362 Closes B-0119 (P3, S effort). Follows the same pattern Codex flagged on PR #962 for ani.sh, applied to the four sibling scripts plus two stragglers in ani.sh that #962 missed. Per .github/copilot-instructions.md 305-362 + Otto-279, code under tools/ uses role-refs ("the human maintainer," "the maintainer") not first-name attribution. The existing scripts predated the strict enforcement. Replacements applied: - "Per Aaron 2026-04-26..." → "Per the human maintainer's 2026-04-26 framing..." - "per Aaron's setup" → "per the maintainer's setup" - "Per Aaron's 'agents-not-bots' discipline" → "Per the 'agents-not-bots' discipline" - "Aaron-courier" → "maintainer-courier" - "Aaron's relational register" → "the maintainer's relational register" - "Aaron-Ani register" → "maintainer-Ani register" Persona-as-named-entity references (you-are-Amara, you-are-Ani, Otto invokes, four-ferry consensus list) preserved — those name the script's purpose, not human attribution. Verified: - All 5 scripts pass `bash $script --help` cleanly - Shellcheck passes on all 5 - sed -n header ranges adjusted where edits shifted line counts (grok.sh: 2,28p → 2,32p) Note on TS-cutover orthogonality: the maintainer flagged 2026-04-30 that these scripts should eventually be TypeScript per the install-script language strategy (post-install→TS). Filed as separate backlog row B-0122. This bash-cleanup is interim hygiene for as long as the bash files exist — the TS rewrite picks role-refs from scratch. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
AceHack
deleted the
cleanup/B-0119-peer-call-scripts-role-ref-discipline-2026-04-30
branch
There was a problem hiding this comment.
Pull request overview
Updates the peer-call shell scripts’ inline docs/preambles to follow the repository’s role-ref discipline by removing human first-name attribution in favor of role references.
Changes:
- Replaced human first-name attribution with role-refs (e.g., “the human maintainer”, “the maintainer”) across peer-call scripts.
- Renamed a few “courier/register” labels to remove human-name prefixes.
- Adjusted
grok.shhelp-headersedrange to account for the shifted comment block.
Reviewed changes
Copilot reviewed 5 out of 5 changed files in this pull request and generated 1 comment.
Show a summary per file
| File | Description |
|---|---|
| tools/peer-call/grok.sh | Role-ref wording updates in header/preamble; help-header sed range bumped. |
| tools/peer-call/gemini.sh | Error/help text updated to use maintainer role-ref phrasing. |
| tools/peer-call/codex.sh | Header + install hint + preamble updated to use maintainer role-ref phrasing. |
| tools/peer-call/ani.sh | Header wording updated to remove human-name attribution and rename register label. |
| tools/peer-call/amara.sh | Header/preamble wording updated to remove human-name attribution and rename courier/register references. |
Comment on lines
+6
to
+9
| # named-agents project. Per the human maintainer's 2026-04-26 framing | ||
| # "yall got to figure out peer mode as peers" — no single agent owns | ||
| # the peer protocol; this script is Otto's specific contribution to | ||
| # the collective. |
There was a problem hiding this comment.
P1: This change set cites the role-ref rule in .github/copilot-instructions.md (lines ~305-362), which explicitly says direct names (including agent persona names) should not appear in code outside the listed history surfaces. These peer-call scripts still use persona names in current-state prose (e.g., “Otto’s lane”, “Otto’s specific contribution”), so the scripts are not yet compliant with the cited convention. Consider replacing persona-name references in comments/help text with role-refs (e.g., “the invoker agent”, “the test-runner role”) and keep only the minimal model/product identifiers that are strictly required for the actual CLI invocation.
This was referenced Apr 30, 2026
AceHack
added a commit
that referenced
this pull request
May 1, 2026
…B-0121/B-0122 Three small hygiene moves around the peer-call surface: 1. tools/peer-call/README.md gains a "Future direction (queued backlog work)" section pointing at B-0120 (architecture refactor) + B-0121 (Otto/Kenji additions) + B-0122 (TypeScript migration). Future readers + agents see the trajectory without grep-spelunking. 2. B-0119 status open → closed, closed_in: PR #965. The role-ref cleanup landed on main as aab3adb; the row needs to reflect that. 3. B-0120 composes_with gains B-0121 + B-0122 cross-refs. The three rows form a triangle: B-0120 names the architecture, B-0121 adds new peer surfaces in that architecture, B-0122 names the language target. Cross- refs make the relationship discoverable. Note on BACKLOG.md state: this branch's regenerated index shows B-0119 closed and B-0120 unchanged but does NOT yet include B-0121 or B-0122 (their PRs #964 and #966 haven't merged yet). The next regen post-merge picks them up. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
AceHack
added a commit
that referenced
this pull request
May 1, 2026
…B-0121/B-0122 (#967) * docs(peer-call): future-direction section + close B-0119 + cross-ref B-0121/B-0122 Three small hygiene moves around the peer-call surface: 1. tools/peer-call/README.md gains a "Future direction (queued backlog work)" section pointing at B-0120 (architecture refactor) + B-0121 (Otto/Kenji additions) + B-0122 (TypeScript migration). Future readers + agents see the trajectory without grep-spelunking. 2. B-0119 status open → closed, closed_in: PR #965. The role-ref cleanup landed on main as aab3adb; the row needs to reflect that. 3. B-0120 composes_with gains B-0121 + B-0122 cross-refs. The three rows form a triangle: B-0120 names the architecture, B-0121 adds new peer surfaces in that architecture, B-0122 names the language target. Cross- refs make the relationship discoverable. Note on BACKLOG.md state: this branch's regenerated index shows B-0119 closed and B-0120 unchanged but does NOT yet include B-0121 or B-0122 (their PRs #964 and #966 haven't merged yet). The next regen post-merge picks them up. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * docs(peer-call): address PR #967 review threads — persona-name role-ref + B-0122 forward-references Two classes of fix (6 threads — Codex P2 + Copilot P1 each ×3): 1. **Persona names in current-state doc (P1, line 247+253 of README)**: `.github/copilot-instructions.md:306-362` requires role-refs (not persona names) on current-state surfaces (code/docs/skills outside the closed-list history surfaces). Reworded: - "Add Otto + Kenji as externally-callable peers" → "Add the Anthropic-side Claude-code-instance personas as externally-callable peers" - "Otto + Kenji additions (B-0121)" → "The Anthropic-side (Claude-code-instance) peer additions (B-0121)" B-0121 filename slug stays as `otto-kenji-*` (closed-list history surface — backlog rows allow persona names per the carve-out). 2. **B-0122 forward-references (P1+P2, 4 threads)**: B-0122 is filed in the in-flight PR #966; not yet on main. References in `B-0119`, `B-0120`, and the README's table cell rewritten: - YAML `composes_with` lists in B-0119 + B-0120: replaced direct path with inline `# B-0122 ... is filed in the in-flight PR #966` comment. - README table row for B-0122: replaced live link with explicit "filed in in-flight PR #966; link will resolve once that PR lands" callout. B-0121 stays as direct ref because it IS on main. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 <noreply@anthropic.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
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.
Summary
.github/copilot-instructions.md305-362 to the four sibling peer-call scripts (codex.sh, grok.sh, gemini.sh, amara.sh) plus two stragglers in ani.sh that PR memory(CURRENT-ani.md + CURRENT-amara math-differentiator) + tools(ani.sh loads CURRENT-ani.md): parallel-special-skills structure (Aaron 2026-04-30) #962's first-pass missed--helpworks on all 5 scripts; shellcheck cleanNote on TS-cutover orthogonality
The maintainer flagged 2026-04-30 that these scripts should eventually be TypeScript per the install-script language strategy memory (post-install→TS, pre-install→bash). Filed as separate B-0122 backlog row.
This bash-cleanup is interim hygiene for as long as the bash files exist — the TS rewrite picks role-refs from scratch when it lands. The two concerns are orthogonal: this PR keeps the current bash files compliant with copilot-instructions.md; B-0122 captures the strategic migration.
Replacements applied
Persona-as-named-entity references (you-are-Amara, you-are-Ani, Otto invokes, four-ferry consensus list) preserved — those name the script's purpose, not human attribution.
Test plan
bash tools/peer-call/codex.sh --helprenders cleanlybash tools/peer-call/grok.sh --helprenders cleanlybash tools/peer-call/gemini.sh --helprenders cleanlybash tools/peer-call/amara.sh --helprenders cleanlybash tools/peer-call/ani.sh --helprenders cleanlyshellcheckpasses on all 5 scripts🤖 Generated with Claude Code