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 assessing-release-readinessgit 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/assessing-release-readiness)<a href="https://agentmods.dev/skills/jaktestowac/awesome-copilot-for-testers/assessing-release-readiness"><img src="https://agentmods.dev/badge/skills/jaktestowac/awesome-copilot-for-testers/assessing-release-readiness/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/assessing-release-readiness"><img src="https://agentmods.dev/badge/skills/jaktestowac/awesome-copilot-for-testers/assessing-release-readiness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 126 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00076 | $0.02092 |
| Opus 5 | $0.00038 | $0.01046 |
| Sonnet 5 | $0.00015 | $0.00418 |
| Haiku 4.5 | $0.00008 | $0.00209 |
Grade A, and why
assessing-release-readiness 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Assessing Release Readiness
Use this skill when a decision to ship has to be made and someone needs to state what is known, what is not, and what happens if the unknown part goes wrong.
Readiness is not "all tests are green". Green means the tests that exist passed. The question is whether the evidence covers the risk, and where it does not, whether the residual risk is acceptable and recoverable. A recommendation without a stated residual risk is not a recommendation, it is a hope.
When to Use
- a release candidate needs sign-off
- someone asks "are we ready to ship this"
- a go/no-go meeting needs an evidence pack rather than opinions
- a hotfix needs a faster version of the same judgement
- a release shipped badly and the team wants a repeatable gate next time
Operating Principles
- Recommend, do not decide. The recommendation is the tester's; the decision belongs to whoever owns the consequences. Make the trade explicit so they can own it.
- Evidence or a gap, never a blank. Every criterion is met, not met, or unverified. Unverified is a distinct and reportable state.
- Coverage is judged against risk, not against percentage. Ninety percent coverage of low-risk code and none of the payment path is a no-go dressed as a go.
- Recoverability offsets uncertainty. A change with a tested rollback and a feature flag tolerates far more residual risk than one without.
- Absence of evidence is a finding. "No one tested the migration on production-sized data" belongs in the report, in bold.
- The recommendation survives contact with the reader. Someone who was not involved can read it and reach the same conclusion.
Workflow
Phase 0: Fix the scope
Establish and write down:
- the exact build: version, commit, artifact, and where it is deployed
- what changed since the last release, from the changelog or diff
- who the release affects: all users, a cohort, one region, internal only
- the release mechanism: big bang, staged rollout, feature-flagged, canary
- the deadline and what is driving it
What ships with it
3 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 · 165 lines · 76 tokens per session scan A 48bfc3c37402
assessing-release-readiness is a skill published in the GitHub repository jaktestowac/awesome-copilot-for-testers (113 stars, last pushed 15d ago), licensed MIT. It adds 76 tokens to every session and 2,092 once invoked, about $0.0004 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
Git CLI
Help with safe Git workflows (branching, rebasing, release tags) and troubleshooting.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
skill-ship
Package and finalize completed work for delivery — use when a feature is done and ready to ship.
skill-rollback
Roll back to a previous checkpoint via git — use when a change went wrong and you need to revert.
verify-and-ship
Run all quality checks (tests, lint, typecheck), fix failures, update the changelog, commit, push, and create/update the pull request or merge request.
release
Release a new version of the DevoxxGenie IntelliJ plugin — prompt for the target version, bump it in the build files, write a curated CHANGELOG.md entry and plugin.xml change-notes from the git/PR history since the last tag, build to verify, then commit, tag, and publish a matching GitHub release. Use this whenever…