agentmods.dev

Acu: Skill for Claude Code

.claude/skills/acu-check/SKILL.md

acu-check is a skill for Claude Code from Acquiredl/Acu. It costs 40 tokens per session (3,894 once invoked), scanned A, original, MIT.

A read-only scanner that checks the structure and health of workflow pipelines against the current shared templates. It reports missing parts, old template versions, and rule violations without editing files.

In plain words
What is it for?
Use it to scan all pipelines for metadata, required scripts, completion checks, directory conventions, and other structural requirements.
Why use it?
It shows which pipelines need attention while leaving the project unchanged.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions CLAUDE.md.

This is Acquiredl/Acu's own configuration. It tells Claude Code how to work on Acu itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Acu configures →

not rated 2repo 2mo ago A scan 40 tokens original MIT
View source ↗ Acquiredl/Acu
Reuse

Borrowing it

Nothing to install: this file belongs to Acquiredl/Acu. 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/Acquiredl/Acu/master/.claude/skills/acu-check/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Acquiredl/Acu

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.

agentmods badge for acu-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/acquiredl/acu/acu-check/github.svg)](https://agentmods.dev/skills/acquiredl/acu/acu-check)
Your own site
<a href="https://agentmods.dev/skills/acquiredl/acu/acu-check"><img src="https://agentmods.dev/badge/skills/acquiredl/acu/acu-check/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 acu-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/acquiredl/acu/acu-check"><img src="https://agentmods.dev/badge/skills/acquiredl/acu/acu-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,894 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 $0.00040 $0.03894
Opus 5.5 $0.00016 $0.01558
Sonnet 5.5 $0.00008 $0.00779
Haiku 4.5 $0.00004 $0.00389

Measured 2mo ago against content hash decfb42a2d7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

acu-check 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 2mo 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.

.claude/skills/acu-check/SKILL.md · 363 lines

How it starts

The opening of the file, as written. The whole thing — 363 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/acu-check — Pipeline Health Scanner

Read-only diagnostic skill. Scans all pipelines under pipelines/ and reports structural health relative to the current template set. Never modifies files.

Protocol

Step 1: READ — Load current version

  1. Read _templates/VERSION to get the current template version string.
  2. Read pipelines/CLAUDE.md to identify all pipeline directories.

Step 2: SCAN — For each pipeline, run all 22 checks

For each pipeline directory found under pipelines/:

Check 1: Metadata / Version
  • Does .acu-meta.yaml exist at the pipeline root?
    • Yes: Does template_version match _templates/VERSION?
      • Match → [CURRENT] {version}
      • Mismatch → [OUTDATED] {old version} (current: {new version})
    • No: [PRE-VERSIONING] — no metadata, generated before Phase 1
Check 2: gates/advance.sh exists
  • File present → [PASS]
  • File absent → [FAIL]
Check 3: Completion gate exists
  • At least one file matching gate-*-complete.sh in gates/ → [PASS] {filename}
  • None found → [FAIL]
Check 4: Stage directory convention
  • Count directories at pipeline root matching ^[0-9]+- pattern.
    • 2 or more → [PASS] {N} dirs follow {N}-{Name}/ convention
    • 1 → [WARN] only 1 stage dir found
    • 0 → check if pipeline uses an alternative layout (e.g., playbooks/):
      • Alternative layout present → [WARN] uses non-standard layout ({dirname}/) — not {N}-{Name}/
      • Nothing → [FAIL] no stage directories found
  • Note: If .acu-meta.yaml contains stage-dir-naming in known_deviations, downgrade FAIL/WARN to a suppressed notice.
Check 5: templates/intake.yaml and templates/status.yaml exist
  • Both present → [PASS] intake.yaml, status.yaml present
  • One missing → [FAIL] missing {filename}
  • Both missing → [FAIL] templates/intake.yaml and templates/status.yaml not found
Check 6: Sample unit directory exists
  • Look for any directory matching 001-* or 001 pattern in the units directory (check posts/, recipes/, engagements/, or the first {N}-{Name}/ dir for a units subdir).
  • Found → [PASS] {relative-path}/
  • Not found → [WARN] no sample unit directory found

Read the full file on GitHub · 363 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. 2mo ago First seen · 363 lines · 40 tokens per session scan A decfb42a2d7f

Subscribe to this mod's changes

acu-check is a skill published in the GitHub repository Acquiredl/Acu (2 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 3,894 once invoked, about $0.0002 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 2026-08-31.

CI and CDDevOps and cloud
Related

acu-check compared with skills from other repositories

acu-check next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
acu-checkAcquiredl/AcuSkill22mo agoMITA40Claude Code
chinese-git-workflowjnMetaCode/superpowers-zhSkill8.5k11d agoMITA69Claude Code
atmos-profilescloudposse/atmosSkill1.4kyesterdayApache-2.0A35Claude Code
webhook-managementhoangsonww/Claude-Code-Agent-MonitorSkill1.1kyesterdayMITA56Claude Code, Codex
monorepo-managementwshobson/agentsSkill42kyesterdayMITC54Claude Code
managing-github-actions-secretsPostHog/posthog-fossSkill728yesterdayMITA67Claude Code, Codex
postman-newman-automationLambdaTest/agent-skillsSkill390yesterdayMITA156Claude Code, Codex