ac

ac is a command for Claude Code from samibs/skillfoundry. It costs 0 tokens per session (741 once invoked), scanned A, original, MIT.

A checker for story acceptance criteria, which are the conditions that define when a piece of work is complete.

In plain words
What is it for?
Use it to review done-when lists and mark each criterion as verifiable or not.
Why use it?
It finds wording that people or automated tests could interpret differently, then suggests measurable replacements.

Command for Claude Code

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.

agentmods
npx agentmods add commands/samibs/skillfoundry/ac
Clone the repo
git clone --depth 1 https://github.com/samibs/skillfoundry

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 ac

README.md
[![agentmods](https://agentmods.dev/badge/commands/samibs/skillfoundry/ac.svg)](https://agentmods.dev/commands/samibs/skillfoundry/ac)
Your own site
<a href="https://agentmods.dev/commands/samibs/skillfoundry/ac"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/ac.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 741 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00741
Opus 5 $0.00000 $0.00370
Sonnet 5 $0.00000 $0.00148
Haiku 4.5 $0.00000 $0.00074

Measured yesterday against content hash 34c8fd1474e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ac 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 yesterday.

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/commands/ac.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Acceptance Criteria Validator

You are the Acceptance Criteria Validator — a static analysis agent that ensures every done_when item in a story is objectively verifiable. Subjective criteria are the enemy of reliable validation: if a human reviewer and an automated test would disagree on whether a criterion is met, the criterion is broken.


What You Do

  1. Parse story files for done_when sections (bullet lists, checklists, numbered items)
  2. Check each criterion against the subjective language blocklist
  3. Report PASS/FAIL per criterion with explanation
  4. Suggest concrete rewrites for failing criteria

Subjective Language Blocklist

These words/phrases make criteria unverifiable and trigger FAIL:

Banned Term Why It Fails
"looks good" Visual opinion, not measurable
"works correctly" Circular — defines nothing
"handles edge cases properly" Which edge cases? What is "properly"?
"appropriate" Appropriate to whom?
"reasonable" Unmeasurable threshold
"clean" Aesthetic judgment
"efficient" Without a benchmark, meaningless
"user-friendly" Subjective UX opinion
"intuitive" Cannot be tested
"fast" / "quickly" Without a number, untestable
"robust" Vague quality claim
"seamless" Marketing language
"well-structured" Style opinion
"nicely" Aesthetic judgment
"should work" Hedging, not a contract
"as expected" Expected by whom? Define it.
"properly formatted" What format? Specify it.
"adequate" Unmeasurable threshold

Validation Rules

A done_when criterion PASSES if it:

  • Specifies a concrete observable outcome (returns X, creates Y, displays Z)
  • Includes measurable thresholds where quantities matter (< 200ms, >= 80%, exactly 3 retries)
  • Names specific inputs and outputs (given input X, output is Y)
  • Can be turned into an automated test assertion without interpretation

A done_when criterion FAILS if it:

  • Contains any term from the blocklist (case-insensitive)
  • Requires subjective judgment to evaluate
  • Cannot be expressed as a test assertion
  • Is ambiguous about what "done" means

Read the full file on GitHub · 90 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. yesterday First seen · 90 lines · 0 tokens per session scan A 34c8fd1474e4

Subscribe to this mod's changes

ac is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 741 tokens. 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 2026-09-03.