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.
npx skills add majiayu000/claude-skill-registry --skill ac-lockgit clone --depth 1 https://github.com/majiayu000/claude-skill-registryWrote 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.
[](https://agentmods.dev/skills/majiayu000/claude-skill-registry/ac-lock)<a href="https://agentmods.dev/skills/majiayu000/claude-skill-registry/ac-lock"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/ac-lock/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.
<a href="https://agentmods.dev/skills/majiayu000/claude-skill-registry/ac-lock"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/ac-lock.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00057 | $0.01705 |
| Opus 5 | $0.00028 | $0.00852 |
| Sonnet 5 | $0.00011 | $0.00341 |
| Haiku 4.5 | $0.00006 | $0.00170 |
Grade A, and why
ac-lock 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AC Lock Checkpoint
Runs automatically as Phase 4.0, after Tasks Validation and before the first implementation task. Purpose: give the user one final explicit confirmation that the Acceptance Criteria represent what they actually want — before any implementation begins.
Position in flow
[Tasks Validation]
↓
[AC Lock Checkpoint] ← THIS SKILL
↓
Per-Task: implementation
Entry conditions
prd.md,techspec.md, andtasks.mdmust exist intasks/prd-{slug}/- Generates
accepted-criteria.mdin.claude/feature-state/{slug}/ - If
accepted-criteria.mdalready exists (resume case): skip extraction, ask user to confirm current locked ACs or unlock to re-confirm - Implementation must not start until this file is saved
Step 1: Extract and Consolidate ACs
Sources
Read ACs from all three documents:
From prd.md:
- "Goals" or "Objectives" section (functional success criteria)
- "Acceptance Criteria" section (if present)
- "Success Metrics" section (if present)
From techspec.md:
- "Validation & Testing Plan" section
- "Acceptance Criteria" section (if present)
- Non-functional requirements that can be verified
From tasks.md:
- "Acceptance Criteria" or "Done When" column/field per task
- Any inline criteria in task descriptions
Deduplication
Merge near-duplicate ACs (same intent, slightly different wording):
- "trainerId is saved to Firestore" + "trainerId is persisted on student document" → consolidate as one
- Use the more specific/verifiable version
Classification
Group ACs into three categories:
-
Functional — observable user/system behavior
- e.g., "Trainer can see their connected students in /cms/students"
-
Technical — implementation-level verifiable criteria
- e.g., "POST /api/students saves trainerId field"
- e.g., "Firestore security rules validated"
-
Quality — non-functional, cross-cutting
- e.g., "All use cases have unit tests"
- e.g., "No breaking changes to existing API consumers"
What ships with it
1 file 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.
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.
- 11d ago First seen · 239 lines · 57 tokens per session scan A 4aacff1a01cd
ac-lock is a skill published in the GitHub repository majiayu000/claude-skill-registry (600 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 1,705 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
remotion-docs
Search and fetch Remotion documentation pages.
remotion-captions
Dealing with captions in Remotion.
remotion-render
Best practices for rendering videos.
academy-guide
Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude…
remotion-maps
Remotion Map animation knowledge.
mediabunny
Multimedia handling with the Mediabunny library.