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 jaktestowac/awesome-copilot-for-testers --skill tracing-requirements-to-codegit clone --depth 1 https://github.com/jaktestowac/awesome-copilot-for-testersWrote 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/jaktestowac/awesome-copilot-for-testers/tracing-requirements-to-code)<a href="https://agentmods.dev/skills/jaktestowac/awesome-copilot-for-testers/tracing-requirements-to-code"><img src="https://agentmods.dev/badge/skills/jaktestowac/awesome-copilot-for-testers/tracing-requirements-to-code/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/jaktestowac/awesome-copilot-for-testers/tracing-requirements-to-code"><img src="https://agentmods.dev/badge/skills/jaktestowac/awesome-copilot-for-testers/tracing-requirements-to-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00109 | $0.02713 |
| Opus 5 | $0.00055 | $0.01357 |
| Sonnet 5 | $0.00022 | $0.00543 |
| Haiku 4.5 | $0.00011 | $0.00271 |
Grade A, and why
tracing-requirements-to-code 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 7d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tracing Requirements to Code
Use this skill when the tests already exist and the question is what they actually verify.
Traceability is usually taught forward: take a specification, derive requirements, plan tests. That is requirements-test-coverage-mapper, and it is the right skill when you start from a document. This skill handles the other and more common situation: a live codebase, hundreds of tests, requirements scattered across a tracker and three documents, and no reliable statement of which test proves what.
The insistence that makes this worth doing: a traceability link is a claim, not a record. A test tagged @req REQ-014 claims to verify REQ-014, and nothing about writing the tag makes that true. An unverified matrix is worse than no matrix, because it converts ignorance into documented confidence, and it is exactly the artifact people reach for when deciding what not to test.
When to Use
- a suite exists and nobody can say which requirement a given test serves
- someone asks "which tests cover this requirement" and the answer takes a day
- a matrix was built once, was accurate that week, and has not been true since
- a requirement is changing and its affected tests must be found
- tests exist that nobody can trace to any requirement
- an audit, certification, or customer questionnaire needs coverage evidence
Operating Principles
- Traceability runs both ways. Requirement to test finds coverage gaps. Test to requirement finds orphan tests, and nobody looks in that direction.
- A link is verified or it is a guess. The test must fail when the requirement's behaviour is broken. Until it has been seen to, the link is unconfirmed and labelled as such.
- Extract from evidence, not from titles. A test called "validates the discount rule" is a hypothesis about what it does. The assertions are the evidence.
- The matrix lives in the code, not in a spreadsheet. A link stored beside the test moves when the test moves. A link in a document rots the first time anyone refactors.
- Orphans are findings in both directions. An uncovered requirement is a coverage gap. An orphan test is either an undocumented requirement or a test of nothing, and both are worth knowing.
- Drift is the default. Links rot silently through renames, deletions, and refactors. Without a CI check, the matrix is accurate on the day it is written and decreasingly true afterwards.
What ships with it
4 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.
- 7d ago First seen · 189 lines · 109 tokens per session scan A 340fe4b28427
tracing-requirements-to-code is a skill published in the GitHub repository jaktestowac/awesome-copilot-for-testers (113 stars, last pushed 15d ago), licensed MIT. It adds 109 tokens to every session and 2,713 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
fix-tests
Focus on all unit + command tests (pytest --exclude tests/integration). Make sure they pass and fix errors. If you run into anything very odd: stop, and let me know. Mutate test code first and let me know if you think you should update application code.
character-animation-qa
Review local character animation with schema checks, Playwright browser previews, frame sampling, and FFmpeg/ffprobe final output checks.
migrate-xunit-to-xunit-v3
Migrate .NET test projects from xUnit.net v2 to xunit.v3 and fix v3 breaks. Use for package/CPM conversion, OutputType=Exe, preserving the VSTest or MTP runner (including projects currently using YTest.MTP.XUnit2), incompatible TFMs, async void tests, string-to-Type attributes, custom Fact/Theory/BeforeAfterTest…
nunit
Write, run, or repair .NET tests that use NUnit. Use when a repo uses NUnit, [Test], [TestCase], [TestFixture], or NUnit3TestAdapter for VSTest or Microsoft.Testing.Platform execution. USE FOR: writing or reviewing NUnit tests; using [Test], [TestCase], [TestFixture], [SetUp], [TearDown] attributes; configuring…
crap-score
Calculates CRAP (Change Risk Anti-Patterns) for a named .NET method, class, or file. USE FOR: explicit CRAP calculation or coverage-and-complexity risk within that named target, including which tests to prioritize. DO NOT USE FOR: project-wide coverage/CRAP, plateaus, or project-wide blockers/priorities…
michel-create-packmind-dataset
Seed a local Packmind instance with a realistic dataset — one organization populated with standards, commands, and skills — so an autonomous agent can exercise its own changes against lifelike data instead of an empty app. Use this whenever you need populated Packmind data to verify a change end-to-end: reproducing a…