What is feedback-composer?

A template workflow for turning several review reports into one precise feedback document for an outsourced coding agent. It organizes issues by priority and includes file locations, problems, expected results, fixes, and a cause category.

It helps consolidate review findings, rank them from critical to low priority, point to affected files and lines, and state the required fix.

It removes the need to combine scattered review comments into instructions an agent can act on in one pass. It also makes unclear or incomplete feedback easier to identify.

feedback-composer — Skill for Claude Code by myrtlepn

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.

Any agent

npx skills add myrtlepn/gran-maestro --skill feedback-composer

Clone the repo

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

Made for: Claude Code.

Or install mst, the plugin that ships this one along with the rest of its 42 skills, 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/skills/myrtlepn/gran-maestro/feedback-composer/github.svg)](https://agentmods.dev/skills/myrtlepn/gran-maestro/feedback-composer)

Your own site

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

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/myrtlepn/gran-maestro/feedback-composer"><img src="https://agentmods.dev/badge/skills/myrtlepn/gran-maestro/feedback-composer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 905 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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 5.1	$0.00060	$0.00905
Opus 5	$0.00030	$0.00452
Sonnet 5	$0.00012	$0.00181
Haiku 4.5	$0.00006	$0.00090

Measured 8d ago against content hash 7b841ca0e217, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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.

plugins/mst/skills/feedback-composer/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mst:feedback-composer

리뷰 결과를 분석해 외주 에이전트가 한 번에 수정할 수 있는 정밀하고 실행 가능한 피드백 문서를 작성하는 템플릿 스킬입니다. PM Conductor가 변수를 치환하여 /mst:codex로 실행합니다.

실행 프로토콜

<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}

Summary

{N} issues found. {M} critical. Routing to Phase {2|1}. </output_format>

<failure_modes_to_avoid>

Vague feedback: "The code has issues." Instead: specific file, line, problem, fix.
Missing root cause: Always classify whether it's implementation or spec problem.
Forgetting carry-forward: Always check previous feedback rounds for unresolved issues.
Contradictory instructions: Ensure each fix instruction is consistent with others. </failure_modes_to_avoid> </feedback_composer>

Read the full file on GitHub · 109 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.

8d ago First seen · 109 lines · 60 tokens per session scan A 7b841ca0e217

Subscribe to this mod's changes

feedback-composer is a skill published in the GitHub repository myrtlepn/gran-maestro (24 stars, last pushed 20d ago), licensed MIT. It adds 60 tokens to every session and 905 once invoked, about $0.0003 per session on Opus 5. 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

autoreview

Pre-commit/ship code review: Codex default; optional Claude or Pi.

openclaw/clawhub · 20 tokens

rework-rate

Measure and interpret PR rework rate — the emerging 5th DORA metric.

bradygaster/squad · 20 tokens

omh-code-review

This is a Hermes-native code-review workflow skill.

rlaope/oh-my-hermes · 46 tokens

revdiff-plan

Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…

umputun/revdiff · 84 tokens

code-reviewer

Code review specialist focused on patterns, bugs, security, and performance.

RightNow-AI/openfang · 17 tokens

agent-teams-simplify-and-harden

Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…

LeoYeAI/openclaw-master-skills · 115 tokens