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 test-per-ac-plannergit 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/test-per-ac-planner)<a href="https://agentmods.dev/skills/eliyce/paqad-ai/test-per-ac-planner"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/test-per-ac-planner/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/test-per-ac-planner"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/test-per-ac-planner.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 | $0.00645 |
| Opus 5 | $0.00007 | $0.00322 |
| Sonnet 5 | $0.00003 | $0.00129 |
| Haiku 4.5 | $0.00001 | $0.00064 |
Grade A, and why
test-per-ac-planner 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What It Does
Maps each acceptance criterion to the narrowest useful verification path so important behavior does not reach implementation without a proof strategy.
Use This When
Use this after acceptance criteria exist and before coding or handoff, especially when the work spans multiple layers or mixes automated and manual verification.
Inputs
- Read the current acceptance criteria and sequence or story artifact first.
- Read the existing test layout and stack verification guidance for the affected modules.
- Read
references/verification-mapping.mdbefore selecting test layers.
Procedure
- Run
scripts/extract-ac-ids.sh <ac-file>to load the canonical AC id set. - For each AC, choose the smallest test layer that can prove it; reuse existing test patterns/files before proposing new surfaces.
- Assign each test a
T{ac}.{idx}id whose{ac}segment matches the parent AC (script-checked). - Add manual verification only when automation is not practical.
- Format per
assets/output.template.mdand runscripts/check-coverage.sh <ac-file> <plan>to find uncovered ACs; record those under## Uncovered Criteria. - Validate the final markdown with
scripts/lint-output.sh.
Output Contract
- Return a heading named
Verification Plan. - For each criterion, emit a third-level heading combining the AC identifier with its assigned test ids, e.g.
### AC-1.1 → T1.1, T1.2. - Under each heading, provide a table with columns
Test ID,Layer,File,Case, andNotes. - Tests must reference the AC identifier in their test name or enclosing describe block so failure evidence can be traced back via the regex
/AC-\d+(?:\.\d+)?/. - End with
Uncovered Criterialisting any AC identifier that still lacks a viable proof path.
See assets/output.template.md for the canonical shape; lint enforces it.
Escalate / Stop Conditions
- Ask when the available test harness or environment is unknown and materially changes the recommendation.
- Warn when the request expects coverage that the current stack cannot provide without new infrastructure.
- Do not mark a criterion covered if the proposed test only exercises an implementation detail.
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.
- 11d ago First seen · 71 lines · 14 tokens per session scan A 09312ae91714
test-per-ac-planner is a skill published in the GitHub repository Eliyce/paqad-ai (8 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 645 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
auto-qa
QAMESH project QA mesh — plan, run, report, and publish deterministic QA evidence.
auto-canary
A deployment health-check skill for testing whether a recently deployed or staging website is working. It runs build, end-to-end, and browser checks, then reports a pass, warning, or failure.
tdd
A Test-Driven Development guide. TDD means writing a failing test first, adding the smallest implementation that passes it, and then improving the code while keeping the tests passing.
testing-strategy
A testing guide that explains how to combine unit, integration, contract, and end-to-end tests. End-to-end tests check complete user flows, while integration tests check components working together.
debugging
A structured method for finding and fixing software bugs. It starts by writing a test that reproduces the failure, then investigates its underlying cause before making a small fix.
database-verification
Shell-based database connectivity and integrity checks. Verifies that databases are reachable, schemas match expectations, and data integrity constraints hold.