ac-lock

ac-lock is a skill for Claude Code, Codex from majiayu000/claude-skill-registry. It costs 57 tokens per session (1,705 once invoked), scanned A, original, MIT.

A checkpoint skill for confirming a project's acceptance criteria before implementation begins. Acceptance criteria are the specific conditions that must be true for a feature to be considered complete.

In plain words
What is it for?
Use it in projects with PRD, tech-spec, and task files to consolidate requirements, ask for confirmation, and save the agreed criteria before coding.
Why use it?
It prevents implementation from starting with unclear or incomplete success conditions. It gathers criteria from the product requirements, technical specification, and task documents.

Skill for Claude CodeCodex

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

Good fit Use it in projects with PRD, tech-spec, and task files to consolidate requirements, ask for confirmation, and save the agreed criteria before coding.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/majiayu000/claude-skill-registry/ac-lock
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 majiayu000/claude-skill-registry --skill ac-lock
Clone the repo
git clone --depth 1 https://github.com/majiayu000/claude-skill-registry

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 ac-lock

README.md
[![agentmods](https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/ac-lock/github.svg)](https://agentmods.dev/skills/majiayu000/claude-skill-registry/ac-lock)
Your own site
<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.

agentmods 80×15 button for ac-lock

Your own site · 80×15
<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>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,705 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00057 $0.01705
Opus 5 $0.00028 $0.00852
Sonnet 5 $0.00011 $0.00341
Haiku 4.5 $0.00006 $0.00170

Measured 11d ago against content hash 4aacff1a01cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

skills/agent/ac-lock/SKILL.md · 239 lines

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, and tasks.md must exist in tasks/prd-{slug}/
  • Generates accepted-criteria.md in .claude/feature-state/{slug}/
  • If accepted-criteria.md already 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:

  1. Functional — observable user/system behavior

    • e.g., "Trainer can see their connected students in /cms/students"
  2. Technical — implementation-level verifiable criteria

    • e.g., "POST /api/students saves trainerId field"
    • e.g., "Firestore security rules validated"
  3. Quality — non-functional, cross-cutting

    • e.g., "All use cases have unit tests"
    • e.g., "No breaking changes to existing API consumers"

Read the full file on GitHub · 239 lines

Files

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.

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. 11d ago First seen · 239 lines · 57 tokens per session scan A 4aacff1a01cd

Subscribe to this mod's changes

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.