ac

A validator that checks whether a story’s acceptance criteria, the conditions used to decide if work is complete, can be tested objectively. It reports each criterion as pass or fail and suggests rewrites.

In plain words
What is it for?
Use it to inspect done_when lists, flag subjective phrases such as “works correctly,” and rewrite them as measurable conditions.
Why use it?
It catches vague wording that could lead reviewers and automated tests to disagree about whether a task is finished.

Skill for Claude CodeCodex

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 skills/samibs/skillfoundry/ac
Any agent
npx skills add samibs/skillfoundry --skill ac
Clone the repo
git clone --depth 1 https://github.com/samibs/skillfoundry

Made for: Claude Code, Codex.

Per session 5 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 756 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 $0.00005 $0.00756
Opus 5 $0.00003 $0.00378
Sonnet 5 $0.00001 $0.00151
Haiku 4.5 $0.00001 $0.00076

Measured 2d ago against content hash e2fdb524334a, 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 2d 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.

.agents/skills/ac/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 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 · 96 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. 2d ago First seen · 96 lines · 5 tokens per session scan A e2fdb524334a

Subscribe to this mod's changes

ac is a skill published in the GitHub repository samibs/skillfoundry (12 stars, last pushed 1mo ago), licensed MIT. It adds 5 tokens to every session and 756 once invoked, about $0.0000 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.

Related

Other skills, from other repositories

roam

Codebase comprehension via roam-code CLI. Use when exploring codebases, planning modifications, debugging failures, assessing PR risk, or checking architecture health. Triggers on: understanding project structure, pre-change safety checks, finding symbols/files, blast radius analysis, affected tests, health scoring…

Cranot/roam-code · 86 tokens

ring:searching-code

Forensic code search and analysis with optional Chain of Draft (CoD) ultra-concise mode. Five-phase methodology (clarification, planning, execution, analysis, synthesis) with severity assessment. Use for targeted investigation of specific patterns, bugs, or vulnerabilities. Skip for broad architecture mapping (use…

LerianStudio/ring · 74 tokens

ring:exploring-codebases

Exploring a codebase across phases: scopes the target, detects architecture, components, and layers, deep-dives each discovered perspective, then synthesizes findings into actionable guidance with file:line evidence. Use to understand how a feature or system works before planning changes, or to orient on an unfamiliar…

LerianStudio/ring · 91 tokens

ring:writing-skills

Writing or editing a Ring skill: SKILL.md structure, frontmatter and Agent-Search-Optimization rules, token-efficiency targets, and bulletproofing (Iron Law, rationalization tables, Red Flags) so discipline-enforcing skills resist excuses. Use when creating or revising a skill. Delegates pressure-testing to…

LerianStudio/ring · 100 tokens

ring:applying-licenses

Applying or switching a repository's license (Apache 2.0, Elastic License v2, or Proprietary): rewrites the LICENSE file, updates Go/TS source headers, sets SPDX identifiers, and validates consistency after user confirmation. Use when asked to set, apply, or switch a license, or when scaffolding a service with no…

LerianStudio/ring · 94 tokens

ring:auditing-dependency-security

Auditing a dependency for supply-chain risk before install (pip/npm/go/cargo): checks typosquatting, maintainer/age risk, vulnerability DBs (OSV, GHSA, Socket), and lockfile hash pinning, then emits a risk score and approve/conditional/escalate/block decision. Use when adding or updating a dependency, reviewing a…

LerianStudio/ring · 102 tokens