agentmods.dev

controlled-lockcheck-autofix

controlled-lockcheck-autofix is a skill for Claude Code, Codex from EthanYoQ/Skill-hub. It costs 73 tokens per session (412 once invoked), scanned A, original, MIT.

A controlled workflow for repeatedly testing a QQ invoice-grabbing frontend and deciding whether a limited automatic fix is safe. It classifies failures using logs, status files, and truth-audit reports while protecting specified parts of the interface and rules.

In plain words
What is it for?
Use it to prepare and monitor QQ frontend lockcheck runs, classify failed rounds, audit results against reference data, and decide whether an allowed autofix can continue.
Why use it?
It helps unattended test runs distinguish real extraction failures from expected exclusions or blocked changes. This limits unsafe fixes that could alter the approved design or invoice-detection behavior.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 9repo 4d ago A scan 73 tokens original MIT

Good fit Use it to prepare and monitor QQ frontend lockcheck runs, classify failed rounds, audit results against reference data, and decide whether an allowed autofix can continue.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ethanyoq/skill-hub/controlled-lockcheck-autofix
View source ↗ EthanYoQ/Skill-hub
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 EthanYoQ/Skill-hub --skill controlled-lockcheck-autofix
Clone the repo
git clone --depth 1 https://github.com/EthanYoQ/Skill-hub

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.

agentmods badge for controlled-lockcheck-autofix

README.md
[![agentmods](https://agentmods.dev/badge/skills/ethanyoq/skill-hub/controlled-lockcheck-autofix/github.svg)](https://agentmods.dev/skills/ethanyoq/skill-hub/controlled-lockcheck-autofix)
Your own site
<a href="https://agentmods.dev/skills/ethanyoq/skill-hub/controlled-lockcheck-autofix"><img src="https://agentmods.dev/badge/skills/ethanyoq/skill-hub/controlled-lockcheck-autofix/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.

agentmods 80×15 button for controlled-lockcheck-autofix

Your own site · 80×15
<a href="https://agentmods.dev/skills/ethanyoq/skill-hub/controlled-lockcheck-autofix"><img src="https://agentmods.dev/badge/skills/ethanyoq/skill-hub/controlled-lockcheck-autofix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 412 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00073 $0.00412
Opus 5 $0.00036 $0.00206
Sonnet 5 $0.00015 $0.00082
Haiku 4.5 $0.00007 $0.00041

Measured 10d ago against content hash 38d1fe5910e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

controlled-lockcheck-autofix 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 10d 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.

projects/codex-invoice/controlled-lockcheck-autofix/SKILL.md · 34 lines

What it actually says

Controlled Lockcheck Autofix

Project-local skill for unattended QQ frontend lockcheck automation.

Read references/workflow.md first. Read references/failure-taxonomy.md when classifying a failed round. Read references/guardrails.md before proposing or applying any fix.

Hard Boundaries

  • Keep the current frontend design and visible interaction unchanged.
  • Treat tree20260315 as the reference behavior for core invoice-grab rules.
  • Do not expand invoice discovery rules just to chase a failing round.
  • Airbnb and similar non-target documents must keep exclusion evidence, but must not be counted as missing truth invoices.
  • If a candidate fix touches FROZEN or GUARDED ZONE, stop and emit a blocking report instead of editing.

Required Workflow

  1. Prepare an isolated controlled run with prepare_qq_lockcheck_run.py.
  2. Launch monitor and frontend, then rely on controlled autostart instead of manual clicking.
  3. Wait for the round to finish or block.
  4. Run postprocess_qq_lockcheck.py.
  5. Classify the round from process_log.txt, monitor_status.json, strict_truth_audit.json, and qq_lockcheck_report.json.
  6. Only continue unattended iteration when the failure is inside the bounded autofix scope.

Output Expectations

  • Persist per-round classification.json, decision.json, and round_summary.md.
  • Keep run-root evidence paths, top blockers, and packaging-gate metrics in every round summary.
  • State explicitly whether the round passed packaging gate: P0=0 and user_should_review_count<=6.
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.

  1. 10d ago First seen · 34 lines · 73 tokens per session scan A 38d1fe5910e7

Subscribe to this mod's changes

controlled-lockcheck-autofix is a skill published in the GitHub repository EthanYoQ/Skill-hub (9 stars, last pushed 4d ago), licensed MIT. It adds 73 tokens to every session and 412 once invoked, about $0.0004 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.

Claude CodeFrontendTestingagent-workflowai-agentai-promptsautomationcodex
Related

Other skills, from other repositories

playwright-component-testing

Set up component testing with Playwright using a story gallery — scaffold stories and a gallery dev page driven by the built-in mount fixture, no dedicated component-testing runtime. Use when asked to test React or Vue components in isolation with Playwright, or to migrate off @playwright/experimental-ct-react / -vue.

microsoft/playwright · 69 tokens

shipwright-pipeline

Autonomous app builder that converts plain-English descriptions into fully built, tested applications. Use when the user wants to build a new app, scaffold a project, generate a full-stack application, or create an app from a description. Trigger with "build me an app", "create a new app", "shipwright build"…

jeremylongshore/tons-of-skills-marketplace · 80 tokens

live-preview

Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.

SethGammon/Citadel · 40 tokens

qa

QA test your code changes by reading your git diff, choosing the right validation path for frontend/browser and backend changes, and reporting pass/fail with evidence.

Skyvern-AI/skyvern · 33 tokens

testing

Verify a Skyvern deployment is working correctly by smoke-testing the backend API, frontend rendering, browser session provisioning, and workflow execution. Use when the user says 'is Skyvern working', 'test my deployment', 'verify the installation', 'smoke test', or needs to check that a self-hosted or local Skyvern…

Skyvern-AI/skyvern · 71 tokens

e2e-testing

AI-powered E2E testing for any app — Flutter, React Native, iOS, Android, Electron, Tauri, KMP, .NET MAUI. Connects via MCP to running apps so the agent can take screenshots, tap elements, enter text, scroll, inspect UI trees, and verify state with natural language. Use when the user wants to test an app's UI…

ai-dashboad/flutter-skill · 107 tokens