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 attesting-manual-verificationgit 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/attesting-manual-verification)<a href="https://agentmods.dev/skills/jaktestowac/awesome-copilot-for-testers/attesting-manual-verification"><img src="https://agentmods.dev/badge/skills/jaktestowac/awesome-copilot-for-testers/attesting-manual-verification/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/attesting-manual-verification"><img src="https://agentmods.dev/badge/skills/jaktestowac/awesome-copilot-for-testers/attesting-manual-verification.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 | $0.00103 | $0.02026 |
| Opus 5 | $0.00051 | $0.01013 |
| Sonnet 5 | $0.00021 | $0.00405 |
| Haiku 4.5 | $0.00010 | $0.00203 |
Grade A, and why
attesting-manual-verification 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Attesting Manual Verification
Use this skill when a quality practice can only be verified by a person, and the record of that verification needs to be worth something later.
Some practices have no signal. No tool can prove a human explored the product, that a business owner accepted the feature, that a screen reader user could complete the flow, or that a reviewer understood the change. Two bad things happen as a result: the practice gets dropped from the contract because it cannot be automated, or a tool-shaped proxy gets reported as a pass - branch protection counted as "code review done".
An attestation is the honest third option: a dated, attributed statement that a named human verified something, with the evidence attached. It is weaker than a machine check and stronger than an assumption, and it must never be presented as either.
When to Use
- a contract contains
manual-attestationpractices: code review, exploratory testing, UAT, manual accessibility, UX review, observability readiness, groundedness review - a gap matrix shows a human practice and the honest state is neither PRESENT nor MISSING
- release sign-off evidence lives in chat threads and closed tickets
- an audit or handover asks who verified what, against which build
- a team wants credit for real manual work that no tool can see
Operating Principles
- An attestation names a person, not a process. "Reviewed by @maria on 2026-08-19" is an attestation. "We do code review" is a policy.
- It is scoped to a build or a change range. An attestation with no scope drifts forward forever and quietly covers work nobody looked at.
- Evidence, or it is an opinion. Session notes, a charter, a recording, a defect list, a screenshot set, a sign-off message. A link is fine; nothing is not.
- Never derive an attestation from tooling. Branch protection requiring one approval is evidence of a process, not of a specific change being understood. Deriving one is the failure mode this practice exists to prevent.
- Absence is a state, not a failure. "Unattested" is reportable and honest. It is not the same as "not done", and it is not a blocker unless the contract says so.
- Findings from an attested practice cap below blocking. Unattested high-risk work is worth a nudge, not a red build - a gate that blocks on an unprovable property gets switched off, and then nothing is recorded at all.
- Attest before merge, not after release. An attestation collected at sign-off time is a memory exercise.
- An expired attestation is unattested. A UAT sign-off from three releases ago does not cover this build.
What ships with it
1 file 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 · 126 lines · 103 tokens per session scan A 758466d1de28
attesting-manual-verification is a skill published in the GitHub repository jaktestowac/awesome-copilot-for-testers (113 stars, last pushed 15d ago), licensed MIT. It adds 103 tokens to every session and 2,026 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 2026-08-30.
Other skills, from other repositories
skill-coverage-audit
Trace codepaths in diffs, map against tests, auto-generate missing coverage — use before shipping PRs.
gentle-ai-bench
Trigger: bench, journey, journeys, driven mode, gentle-ai-bench, journey corpus, j-numbers, bench axis. Author and verify gentle-ai bench journeys; go test ./bench never proves driven execution.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
code-review
Review .NET changes for bugs, regressions, architectural drift, missing tests, incorrect async or disposal behavior, and platform-specific pitfalls before you approve or merge them. USE FOR: reviewing a pull request or patch in a .NET repository; checking for behavioral regressions, API misuse, or missing tests…
onboard-repo
Index an unfamiliar codebase into the knowledge graph, then produce a first orientation map -- entry points, most-depended-upon modules, hotspots, test topology.
refactor-check
Safety analysis before refactoring -- dependency graph, test coverage, public API exposure, blast radius verdict.