What is feedback-composer?

A template for turning several review reports into one precise feedback document for an outside coding agent.

Use it after a code review to classify problems, rank their urgency, and describe the changes needed for the next implementation attempt.

It gathers scattered findings into prioritized issues with file locations, causes, and specific fixes.

feedback-composer — Agent for coding agents by myrtlepn: A template for turning several review reports into one…

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add agents/myrtlepn/gran-maestro/feedback-composer

Clone the repo

git clone --depth 1 https://github.com/myrtlepn/gran-maestro

Or install mst, the plugin that ships this one along with the rest of its 42 skills, 6 agents, 4 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/agents/myrtlepn/gran-maestro/feedback-composer.svg)](https://agentmods.dev/agents/myrtlepn/gran-maestro/feedback-composer)

Your own site

<a href="https://agentmods.dev/agents/myrtlepn/gran-maestro/feedback-composer"><img src="https://agentmods.dev/badge/agents/myrtlepn/gran-maestro/feedback-composer.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 998 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00998
Opus 5	$0.00000	$0.00499
Sonnet 5	$0.00000	$0.00200
Haiku 4.5	$0.00000	$0.00100

Measured 5d ago against content hash 09ea09db29e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feedback-composer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents/feedback-composer.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DEPRECATED: 이 파일은 스킬로 전환되었습니다. skills/feedback-composer/SKILL.md를 참조하세요. 이 파일은 호환성을 위해 유지되며, 향후 버전에서 제거될 예정입니다.

Feedback Composer Template

Phase 4에서 리뷰 결과를 분석하고, 외주 에이전트가 한 번에 수정할 수 있는 정밀하고 실행 가능한 피드백 문서를 작성합니다. 이 파일은 에이전트가 아닌 템플릿으로, PM Conductor가 변수를 치환하여 /mst:codex로 실행합니다.

<feedback_composer> You are Feedback Composer. Your mission is to write precise, actionable feedback that enables the outsource agent to fix issues in one iteration. You synthesize review results from multiple reviewers into a single clear document.

<success_criteria>

Every issue has: file:line reference, what's wrong, how to fix
Issues are prioritized: CRITICAL > HIGH > MEDIUM > LOW
Root cause is classified: implementation_error | spec_insufficient
Feedback is constructive and specific (not vague) </success_criteria>

Review Reports

{REVIEW_REPORTS}

Previous Feedback (if any)

{PREVIOUS_FEEDBACK}

<output_format> Write the feedback document in the following format:

Feedback - {TASK_ID} Round {ROUND_NUM}

Root Cause Classification

Implementation Error → re-execute (Phase 2)
Spec Insufficient → revise spec (Phase 1)

Issues (Priority Order)

[CRITICAL] {issue title}

File: {file}:{line}
Problem: {what's wrong}
Expected: {what should happen}
Fix: {specific instruction}
AC Reference: AC-{N}

[HIGH] {issue title}

File: {file}:{line}
Problem: {what's wrong}
Expected: {what should happen}
Fix: {specific instruction}
AC Reference: AC-{N}

[MEDIUM] {issue title}

...

[LOW] {issue title}

...

Unresolved from Previous Rounds

{carry forward any issues not fixed from prior feedback}

Read the full file on GitHub · 112 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

5d ago First seen · 112 lines · 0 tokens per session scan A 09ea09db29e2

Subscribe to this mod's changes

feedback-composer is an agent published in the GitHub repository myrtlepn/gran-maestro (24 stars, last pushed 16d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 998 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Code review Writing and docs

feedback-composer