peer-review

A review-analysis workflow that checks another person’s or model’s code-review findings against the actual codebase. It separates confirmed problems from misunderstandings and produces a prioritized action plan.

In plain words
What is it for?
Use it when you receive peer-review feedback, want to cross-check AI-generated findings, or need to decide which confirmed issues should be addressed first.
Why use it?
It prevents teams from accepting incorrect, outdated, or irrelevant review comments without verification.

Skill for Claude CodeCodex

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 skills/tjmustard/hypergraph-coding-agent-framework/hyper-peer-review
Any agent
npx skills add tjmustard/Hypergraph-Coding-Agent-Framework --skill hyper-peer-review
Clone the repo
git clone --depth 1 https://github.com/tjmustard/Hypergraph-Coding-Agent-Framework

Made for: Claude Code, Codex.

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 488 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.

ModelPer sessionOnce invoked
Fable 5 $0.00043 $0.00488
Opus 5 $0.00022 $0.00244
Sonnet 5 $0.00009 $0.00098
Haiku 4.5 $0.00004 $0.00049

Measured 2d ago against content hash 83b549e04e00, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

peer-review 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 2d 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/skills/hyper-peer-review/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Peer Review

This skill critically evaluates external peer review findings as the team lead — verifying each finding against the actual code before accepting or rejecting it.

When to use this skill

  • When another model, reviewer, or team member has provided feedback on the current implementation.
  • When the user explicitly runs /hyper-peer-review and pastes review findings.
  • When cross-checking AI-generated code review output before acting on it.

How to use it

  1. Receive the Findings If feedback was not provided with the command, use AskUserQuestion:

    How would you like to provide the peer review feedback?
    
    - Option A: I'll paste the feedback — type or paste the review content directly
    - Option B: It's already in a file — provide the file path and I will read it
    

    The reviewer has less context on this project's history and decisions than you do — evaluate accordingly.

  2. Verify Each Finding For EACH finding:

    • Check if it exists — Read the actual code. Does this issue really exist?
    • If it doesn't exist — Explain clearly why (already handled, reviewer misunderstood the architecture, outdated assumption).
    • If it does exist — Assess severity: Critical / High / Medium / Low.
  3. Produce the Summary Output three sections:

    Valid Findings (Confirmed Issues)

    • List each confirmed issue with its severity and the specific file/function affected.

    Invalid Findings (Rejected with Explanation)

    • List each rejected finding with a clear explanation of why it's incorrect or inapplicable.

    Prioritized Action Plan

    • Ordered list of confirmed issues to fix, from highest to lowest severity.
    • For each: the specific change needed and which file/node it affects.

Behavior Rules

  • You are the team lead — do not accept findings at face value.
  • Always read the code before accepting or rejecting a finding.
  • Be direct but fair. If a finding is wrong, explain why clearly.
  • Cross-reference spec/compiled/architecture.yml for architectural context when evaluating structural findings.

Read the full file on GitHub · 55 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.

  1. 2d ago First seen · 55 lines · 43 tokens per session scan A 83b549e04e00

Subscribe to this mod's changes

peer-review is a skill published in the GitHub repository tjmustard/Hypergraph-Coding-Agent-Framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 488 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens