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 Eliyce/paqad-ai --skill acceptance-criteria-gengit clone --depth 1 https://github.com/Eliyce/paqad-aiWrote 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/eliyce/paqad-ai/acceptance-criteria-gen)<a href="https://agentmods.dev/skills/eliyce/paqad-ai/acceptance-criteria-gen"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/acceptance-criteria-gen/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/eliyce/paqad-ai/acceptance-criteria-gen"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/acceptance-criteria-gen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00014 | $0.00937 |
| Opus 5 | $0.00007 | $0.00468 |
| Sonnet 5 | $0.00003 | $0.00187 |
| Haiku 4.5 | $0.00001 | $0.00094 |
Grade A, and why
acceptance-criteria-gen 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 6d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What It Does
Turns a scoped request into testable acceptance criteria that describe observable behavior, guardrails, and failure handling without relying on implied implementation details.
Use This When
Use this when a request is entering planning or solutioning and the current brief has goals but not enough precise behavior to verify. It is especially important before stories, test mapping, or handoff artifacts are written.
Inputs
- Read the active request, tracker entry, or plan summary first.
- Read the canonical module docs or feature spec that defines the current behavior.
- Read
references/criteria-template.mdbefore drafting criteria so wording stays consistent.
Procedure
- Run
scripts/extract-ac-ids.sh <spec-file>to get the set of AC ids already taken; never reuse a removed id. - For each new criterion, run
scripts/next-ac-id.sh <spec-file>to allocate the next free flat id. - List the user-visible outcomes and constraints; convert each into one observable Given/When/Then line using
assets/output.template.mdas the shape, ending each line with an explicit(proof: automated|manual|visual)tag. - Surface negative and edge paths with the shared rubric instead of relying on the happy path alone: run
edge-case-detection(runtime/base/skills/edge-case-detection/SKILL.md) over the same request as a sub-step. It is reused as-is — do not clone it — and its category set (empty, stale, loading, retry, permission, concurrency, rollback, integration, overflow, state-skip) already covers the paths acceptance criteria must guard. Follow each returned case'sApply To:routing: fold a case that changes an error, empty, or permission path the request actually touches into a flatAC-nnegative-path criterion here (Given the failing/empty/unauthorized condition, when …, then the observable guard holds); record a case that is a deliberate exclusion — an edge behaviour the change will not handle — under the spec's## Non-goalssection (parsed intoFeatureSpec.non_goals) rather than as a criterion. Drop cases that are not credible for this request, and drop criteria that describe implementation choices instead of behavior. - Validate the draft with
scripts/lint-ac-output.sh <draft-file>— exit 0 means the structural contract is met; non-zero means fix and re-lint before returning.
What ships with it
6 files 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.
- 6d ago Changed · +1 lines 8ba72376d393
- 7d ago Changed · +1 lines 766859151d1a
- 12d ago First seen · 67 lines · 14 tokens per session scan A bff7a16b62b0
acceptance-criteria-gen is a skill published in the GitHub repository Eliyce/paqad-ai (8 stars, last pushed yesterday), licensed MIT. It adds 14 tokens to every session and 937 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
pr-writing-review
Extract and analyze writing improvements from GitHub PR review comments. Use when asked to show review feedback, style changes, or editorial improvements from a GitHub pull request URL. Handles both explicit suggestions and plain text feedback. Produces structured output comparing original phrasing with reviewer…
session-investigator
Investigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debugging tool loops, when correlating sub-agent traces with main sessions, or when analyzing conversation flow and timing. Covers session.json metadata, history JSON format, message structure, tool…
auto-go
A command that implements code from a SPEC, a document describing the required behavior and work.
auto-plan
A code-planning skill that examines a codebase and creates a detailed specification, implementation plan, and acceptance criteria. It can organize requirements using EARS, a structured way to describe how software should behave in different situations.
agent-pipeline
Multi-agent pipeline orchestration skill.
adaptive-quality
Per-task execution profile selection based on complexity in Balanced quality mode.