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 communicating-quality-findingsgit 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/communicating-quality-findings)<a href="https://agentmods.dev/skills/jaktestowac/awesome-copilot-for-testers/communicating-quality-findings"><img src="https://agentmods.dev/badge/skills/jaktestowac/awesome-copilot-for-testers/communicating-quality-findings/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/communicating-quality-findings"><img src="https://agentmods.dev/badge/skills/jaktestowac/awesome-copilot-for-testers/communicating-quality-findings.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 MCP Rug Pull · line 121 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Excessive Agency · line 218 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 | $0.00160 | $0.03633 |
| Opus 5 | $0.00080 | $0.01817 |
| Sonnet 5 | $0.00032 | $0.00727 |
| Haiku 4.5 | $0.00016 | $0.00363 |
Grade A, and why
communicating-quality-findings 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 12d 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Communicating Quality Findings
Use this skill when a QA finding set is already true and still useless, because the person who has to act on it cannot get to the action.
There are two ways a report fails and they need different fixes. A dishonest report says the suite passed when it did not - that is unslop-answers. An unactionable report says everything correctly and gets skimmed, filed, and forgotten. That is this skill. The second failure is quieter and more common, because nothing in the report looks wrong.
This is not "be brief". A one-line report that omits the blocker is worse than the wall of text it replaced.
When to Use
- writing a triage summary, review round-up, release recommendation, or exploratory debrief
- the finding set is long enough that ordering decides what gets fixed
- the same findings need retelling for a different audience or a different decision
- a report was sent and nothing happened
- a bug queue, gap matrix, or traceability matrix needs an accompanying message
- the request mentions "too long", "make this readable", "just tell me what to do", "so what", "TL;DR", "for the stakeholders"
- a stand-up or channel update has to carry the state of a multi-day test effort
Fast Pass
Most output is routine and does not need the full workflow. Four checks, in this order, before sending anything:
- Is the blocker in the first two lines? If there is a thing that stops the reader, that is line two. Not a bullet, not a closing note.
- Did any claim lose its evidence while being shortened? A rung marker, a denominator, or a "not run" line dropped for brevity goes back in. This check outranks the other three.
- Is there more than one decision, or more than five things to act on? Split the message, or move the full set to a file under
.qa/and keep the five. - Does the last line say what happens next, and who does it? Even "open the file" counts.
For a report, a review, a release call, or anything a stakeholder reads, run the full workflow below and the nine-check gate in ./resources/pre-send-gate.md.
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.
- 12d ago First seen · 224 lines · 160 tokens per session scan A 4d715ecb426f
communicating-quality-findings is a skill published in the GitHub repository jaktestowac/awesome-copilot-for-testers (113 stars, last pushed 16d ago), licensed MIT. It adds 160 tokens to every session and 3,633 once invoked, about $0.0008 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
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
cognitive-doc-design
Design docs that reduce cognitive load. Trigger: writing guides, READMEs, RFCs, onboarding, architecture, or review-facing docs.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.