An automated quality check for pull requests in Looper-managed GitHub repositories. A pull request is a proposed code change awaiting review; Looper is the system that manages its worker and reviewer loops.

Use it on eligible labeled pull requests to inspect Looper state, check out the code, review it, run the language-specific tests, and report whether the change passes or needs fixes.

It adds an independent review and test pass so one automated reviewer is not the only check before a person merges the change.

looper-qa — Skill for Claude Code and Codex by quangdang46

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 quangdang46/looper_rust --skill looper-qa

Clone the repo

git clone --depth 1 https://github.com/quangdang46/looper_rust

Made for: Claude Code, Codex.

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/quangdang46/looper_rust/looper-qa.svg)](https://agentmods.dev/skills/quangdang46/looper_rust/looper-qa)

Your own site

<a href="https://agentmods.dev/skills/quangdang46/looper_rust/looper-qa"><img src="https://agentmods.dev/badge/skills/quangdang46/looper_rust/looper-qa.svg" alt="Measured on agentmods" height="20"></a>

Per session 125 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,275 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	$0.00125	$0.03275
Opus 5	$0.00063	$0.01638
Sonnet 5	$0.00025	$0.00655
Haiku 4.5	$0.00013	$0.00328

Measured 6d ago against content hash 66e76870f001, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

looper-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 6d 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.

PORTING-TO-RUST/.hermes/skills/looper-qa/SKILL.md · 319 lines

How it starts

The opening of the file, as written. The whole thing — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Looper QA Cycle (Hermes-driven)

Scheduled QA pass over Looper-managed pull requests. Fills the gap between looperd's own reviewer loop and the human merge step: runs an independent review pass on every PR that carries the looper:qa label, posts a structured verdict back to GitHub, and updates labels so the Looper fixer loop can pick up regressions automatically.

Core principle: No single agent should be the only thing standing between a PR and main. This skill is the independent reviewer.

When to Use

Triggered by Hermes cron every 15 minutes (*/15 * * * *) per Looper project
On demand: looper-qa.sh owner/repo#42
After a Looper worker loop opens a PR — pick the PR up before the human merge
After a Looper reviewer passes — independent second-pass verification
Skip for: documentation-only PRs (no Go/Rust/JS/Python code change), PRs already carrying looper:qa-failed (Fixer owns the next pass), PRs that touch only the dist/ tree

Prerequisites

Required on PATH:

Tool	Purpose	Install check
`looper`	Loop inspection (`ps`, `queue`, `loop failures`)	`looper version`
`gh`	GitHub CLI for labels, reviews, checkout	`gh auth status`
`git`	Worktree-less checkout via `git fetch`	`git --version`
`ffs`	Code review (impact, refs, flow)	`ffs --version`
`hermes`	Owning scheduler (this skill runs inside `hermes cron tick`)	`hermes --version`
`python3`	YAML lint, status parsing	`python3 --version`
One of: `go`, `cargo`, `npm`, `pytest`	Language test runner	auto-detected

Optional:

computer_use MCP tool (UI smoke tests for web/desktop apps)
looperd running locally (only needed for the loop-status probe — graceful skip when unreachable)

State Machine

                    cron tick (every 15 min)
                              |
                              v
                  probe looper ps --json --all
                              |
              +---------------+---------------+
              v               v               v
       no PRs eligible   PR with looper:qa   PR with looper:qa-testing
       (silent exit)     label found         (skip — in progress)
                              v
                  checkout + ffs review + tests
                              v
                  +-----------+-----------+
                  v                       v
           all checks pass        any check fails
                  v                       v
        gh pr review --approve   gh pr review --request-changes
        add looper:qa-passed     add looper:qa-failed
        (human merge)            (Fixer auto-pickup)

Read the full file on GitHub · 319 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

6d ago First seen · 319 lines · 125 tokens per session scan A 66e76870f001

Subscribe to this mod's changes

looper-qa is a skill published in the GitHub repository quangdang46/looper_rust (4 stars, last pushed 18d ago), licensed MIT. It adds 125 tokens to every session and 3,275 once invoked, about $0.0006 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.

Code review Orchestration Testing beads cli developer-tools sqlite

genie-orca-review

Independent, read-only review of a group, a wish, or a PR on Orca — SHIP / FIX-FIRST / BLOCKED with severity-tagged findings. Council and retro are this skill with a different input.

automagik-dev/genie · 50 tokens

argot-check

Score your working changes with argot — flag code foreign to this repo's own patterns (unfamiliar dependencies, APIs, constructs), functions the repo already has, code filed in the wrong place, imports that break the repo's layering, and tests weakened, disabled, or deleted alongside a production change — before…

get-tmonier/argot · 110 tokens

looper-qa