A quality-check workflow that reviews recent code changes against stated acceptance rules. It sends failures back to the original coding agent, records them, and repeats the check after fixes.

It helps inspect a Git diff, compare changes with project rules and acceptance criteria, log failed checks, and escalate unresolved issues.

It provides a clear pass or fail decision without letting the reviewer change the code or skip recording problems.

How lionshilov/Forge configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to lionshilov/Forge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/lionshilov/Forge/main/.claude/skills/forge-qa/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/lionshilov/Forge

Made for: Claude Code.

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/lionshilov/forge/forge-qa/github.svg)](https://agentmods.dev/skills/lionshilov/forge/forge-qa)

Your own site

<a href="https://agentmods.dev/skills/lionshilov/forge/forge-qa"><img src="https://agentmods.dev/badge/skills/lionshilov/forge/forge-qa/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/lionshilov/forge/forge-qa"><img src="https://agentmods.dev/badge/skills/lionshilov/forge/forge-qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 286 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.

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	$0.00034	$0.00286
Opus 5.5	$0.00014	$0.00114
Sonnet 5.5	$0.00007	$0.00057
Haiku 4.5	$0.00003	$0.00029

Measured today against content hash 3d892a558a4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

forge-qa 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 today.

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.

.claude/skills/forge-qa/SKILL.md · 19 lines

What it actually says

You are the Forge Orchestrator running the QA gate.

Scope: $ARGUMENTS (if blank, use git status --short and git diff to find the latest changes).

Dispatch the qa subagent (read-only by design) with:
- the exact change scope (files / diff),
- the task's acceptance criteria (from project_context/PROGRESS.md if tracked),
- the instruction to read project_context/CONVENTIONS.md, ARCHITECTURE.md, INTERFACES.md, SECURITY.md, and ERRORS_LOG.md first.
On PASS — mark the task 🟢 in PROGRESS.md and report the verdict to the user.
On FAIL — append the ERR- entry to ERRORS_LOG.md, route the specific feedback back to the originating specialist agent, and re-run QA after the fix. Max 3 retries, then escalate to the user with full context.

Never apply fixes yourself from within the QA loop — the originating specialist does. Never skip logging a FAIL.

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.

today First seen · 19 lines · 34 tokens per session scan A 3d892a558a4b

Subscribe to this mod's changes

forge-qa is a skill published in the GitHub repository lionshilov/Forge (5 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 286 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-11-07.

Code review LLM Multi-Agent Testing ai-agents anthropic claude

forge-qa next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
forge-qalionshilov/Forge	Skill	5	1mo ago	MIT	A	34	Claude Code
requesting-code-reviewgraniet/kheish	Skill	213	today	Apache-2.0	A	41	Claude Code, Codex
github-code-reviewgraniet/kheish	Skill	213	today	Apache-2.0	A	41	Claude Code, Codex
cpp-coding-standardsaffaan-m/ECC	Skill	299k	today	MIT	A	48	Claude Code, Kiro
coding-standardsaffaan-m/ECC	Skill	299k	today	MIT	A	50	Claude Code, Codex
pr-lensNousResearch/hermes-agent	Skill	261k	today	MIT	A	15	Claude Code, Codex
opencodeNousResearch/hermes-agent	Skill	261k	today	MIT	A	15	Claude Code, Codex

Forge: Skill for Claude Code