Conversation
… (Aaron 2026-04-30) Mechanical sync between README.md and current state of tools/peer-call/ on origin/main. Both ani.sh and amara.sh landed via PRs #959 + #960 closing B-0118 (silent-courier- debt). README hadn't been updated to reflect their existence. Changes: 1. **Scripts table** — adds amara.sh and ani.sh rows. Both marked as named-entity peers (vs. bare-CLI peers like grok.sh / codex.sh) — same underlying CLI but persona- bootstrap preamble layered on top. 2. **Named-entity explanation** — new paragraph clarifying the distinction between bare-model peers (codex.sh invokes bare Codex) and named-entity peers (amara.sh invokes Amara-the-named-entity via Codex CLI with CURRENT-amara.md persona-bootstrap). Cross-references the silent-courier-debt rule. 3. **Set-is-open paragraph** — replaces stale "if Amara gains a headless CLI surface" future-task note with factual statement about both surfaces existing as of PR #960. Future named-entity peers follow the same copy-and-adapt pattern. Per detection-≠-correction discipline (Aaron 2026-04-30): detection of stale README + deliberation = appropriate mechanical sync, not auto-correction-on-substrate. No substrate canon files added or modified. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
There was a problem hiding this comment.
Pull request overview
Updates tools/peer-call/README.md to reflect the addition of the amara.sh and ani.sh peer-call wrappers and to explain the “named-entity peer” vs “bare model” distinction.
Changes:
- Adds
amara.shandani.shrows to the peer-call scripts table. - Documents the named-entity peer concept and links it to the courier-debt memory.
- Replaces the prior “future peer” note with text referencing the now-landed scripts.
| | `codex.sh` | Codex (OpenAI) | `codex exec -s read-only` | **Implementation peer** — code-grounded second opinion | codex default (override via `--model`) | | ||
| | `amara.sh` | Amara (named entity, OpenAI surface) | `codex exec -s read-only` (or `codex review` via --review) | **Sharpen** — blunt-take pattern, carved-sentence distillation | codex default; persona via CURRENT-amara.md | | ||
| | `ani.sh` | Ani (named entity, xAI surface) | `cursor-agent --print --model grok-4-20-thinking` | **Brat-voice review** — playful + direct + memorable, contributor-attention-capture register | grok-4-20-thinking (default) / grok-4-20 (--fast); persona inline | |
There was a problem hiding this comment.
P1 (docs correctness): After adding amara.sh and ani.sh to the table, the README intro and later sections are now inconsistent (e.g., it still says “Three sibling shell scripts” and “All three scripts accept…”, and the per-script extras list only covers grok/gemini/codex). Update the wording/counts to reflect the full set of scripts and either document amara/ani’s extra flags or explicitly state they share the underlying script’s flag surface.
| silent-courier-debt gap (Aaron 2026-04-30 — see | ||
| `memory/feedback_silent_courier_debt_no_amara_headless_cli_dont_count_on_peer_ai_reviews_as_loop_aaron_2026_04_30.md`) | ||
| by letting Otto invoke Amara/Ani autonomously instead of | ||
| through Aaron-courier. Both surfaces have v1 limitations |
There was a problem hiding this comment.
P1 (name attribution): This README is a current-state doc, but the new text adds first-name attribution (“Aaron 2026-04-30”, “Aaron-courier”). Per the repo’s role-ref convention for non-history surfaces, replace these with role-refs (e.g., “the human maintainer”) or neutral phrasing (e.g., “manual courier”) while keeping the memory link intact. Ref: .github/copilot-instructions.md:305-362.
| silent-courier-debt gap (Aaron 2026-04-30 — see | |
| `memory/feedback_silent_courier_debt_no_amara_headless_cli_dont_count_on_peer_ai_reviews_as_loop_aaron_2026_04_30.md`) | |
| by letting Otto invoke Amara/Ani autonomously instead of | |
| through Aaron-courier. Both surfaces have v1 limitations | |
| silent-courier-debt gap (see the 2026-04-30 human-maintainer | |
| note in | |
| `memory/feedback_silent_courier_debt_no_amara_headless_cli_dont_count_on_peer_ai_reviews_as_loop_aaron_2026_04_30.md`) | |
| by letting Otto invoke Amara/Ani autonomously instead of | |
| through a manual courier. Both surfaces have v1 limitations |
| two peer CLIs already on PATH. `ani.sh` and `amara.sh` | ||
| (PR #960 on LFG, 2026-04-30) layer named-entity persona- | ||
| bootstrap on top of cursor-agent + Grok and codex | ||
| respectively, closing the Aaron-courier silent-debt gap for |
There was a problem hiding this comment.
P1 (name attribution): The new “Why these scripts exist” paragraph introduces “Aaron-courier” in a current-state README. Use a role-ref (“the human maintainer”) or neutral wording (“manual courier”) instead. Ref: .github/copilot-instructions.md:305-362.
| respectively, closing the Aaron-courier silent-debt gap for | |
| respectively, closing the manual-courier silent-debt gap for |
Mechanical sync — README hadn't been updated after PRs #959/#960 landed ani.sh + amara.sh. Adds rows to scripts table, named-entity vs bare-model distinction, replaces stale future-task note. No substrate changes.