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 smixs/disruptor-skills --skill qa-demo-standgit clone --depth 1 https://github.com/smixs/disruptor-skillsWrote 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/smixs/disruptor-skills/qa-demo-stand)<a href="https://agentmods.dev/skills/smixs/disruptor-skills/qa-demo-stand"><img src="https://agentmods.dev/badge/skills/smixs/disruptor-skills/qa-demo-stand/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/smixs/disruptor-skills/qa-demo-stand"><img src="https://agentmods.dev/badge/skills/smixs/disruptor-skills/qa-demo-stand.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 | $0.00025 | $0.02590 |
| Opus 5 | $0.00013 | $0.01295 |
| Sonnet 5 | $0.00005 | $0.00518 |
| Haiku 4.5 | $0.00003 | $0.00259 |
Grade A, and why
qa-demo-stand scanned grade A with 1 finding 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.
Asks the agent to reveal its instructionslowSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
prompt injection ("ignore your instructions", role switching, "print your system prompt"); Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA on a demo stand
Stage contract
- Stage: 6. QA to production quality · Kind: prompt
- Inputs: the built, converged project (local/dev).
- Outputs: reproduced + root-caused defects (and fixes, per
FIX_MODE), tested to production quality; a running defect/timeline record. - Entry gate: the build has converged. LOCAL/DEV only — never point at stage/prod; confirm before any destructive chaos.
- Done when: defects reproduced ≥3× with an established cause, criticals surfaced/fixed, and self-heal-vs-broken-state verified for each induced failure.
- Next: the
setup-serverskill. - Note: this is a prompt template — fill its
[PLACEHOLDERS]and hand the whole thing to a fresh executor agent; don't paraphrase it. This is also the entry point for the bug on-ramp (a defect report enters the flow here).
You are a senior QA/Security engineer. Build a local test stand (a "demo stand") for the project [PROJECT_DIR] and test it to production quality: find, reproduce, and record defects, with a focus on infrastructure stability, data isolation, and resilience to failures. Work autonomously and thoroughly; don't spare time or tokens.
Hard rules
- LOCAL/dev environment ONLY ([BASE_URL], default http://127.0.0.1:8080). NEVER point tests or destructive probes at stage/prod. Destructive chaos (killing containers, cutting the network, corrupting configs) — only on local dev containers, with mandatory restoration afterwards.
- The stand lives in a SEPARATE
demostand/folder, excluded from git via.git/info/exclude(don't touch the shared .gitignore; verify withgit check-ignore demostand/). Commit nothing from the stand. - Build the stand FROM SCRATCH and INDEPENDENTLY. Treat existing tests as UNVERIFIED: there is no guarantee they covered all scenarios or are correct. Wherever you can, independently re-verify the behavior they supposedly cover.
- Document-driven: the source of truth is the specs in
demostand/spec/(scenarios, flows, edge cases, security, infra). Scripts and browser agents merely EXECUTE what is described. - Simulate a REAL user through the browser (real login, clicks, input), not only direct API calls.
- A bug = reproduced ≥3 times + an established cause. Only then — report criticals immediately. Fix handling mode: [FIX_MODE: "accumulate everything and fix nothing" OR "fix confirmed ones immediately"]. If you fix — strictly TDD (test→code→run→check for absent regressions) and log to the timeline "what was found / how it was fixed / re-verified". Changes to auth/security/migrations — run an external code review at the very end.
- For every induced failure, check not "did it fall over" but whether the system RECOVERS on its own or wedges into a broken state and requires a restart.
- Before outward-facing/irreversible actions and before chaos on possibly-shared infrastructure — confirm. After browser probes, close sessions and delete screenshots/artifacts.
- Out of scope: [ANY_EXCLUSIONS — features/modes we don't touch; if none — "none"].
- Every couple of hours produce a brief checkpoint report and continue.
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 · 168 lines · 25 tokens per session scan A c0c38089703c
qa-demo-stand is a skill published in the GitHub repository smixs/disruptor-skills (18 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 2,590 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
debug
Run /debug to find and fix a bug's root cause: a test failing for an unclear reason, /check verify finding a failure, or behavior being wrong. Runs a reproduce, localize, hypothesize, test, fix, verify loop, makes the minimal fix, and hands a regression test to /test. No features, no extra refactors.
check
Confirm a change before merge. /check verify drives the real app to prove behavior against the spec (every acceptance criterion met, every surface built). /check review runs a senior code review on a fresh model, one that did not write the code. Verify after /develop, review before a PR. Writes to docs/reviews/, never…
implement
Use when an approved plan and task list exist and it is time to turn them into working, tested code — the SDD phase after analyze and before verify. Enforces TDD: a failing test comes before the code that makes it pass, one task at a time, appended to a progress ledger that survives compaction. Delegates test tooling…
csharp-dotnet
Use when writing, reviewing, testing, or shipping C# / .NET code — ASP.NET Core APIs (minimal APIs vs controllers), EF Core data access, async correctness, solution layout in .cs/.csproj/.sln. NOT a Java/Spring backend (that is spring-boot), NOT a Node/TypeScript backend (that is nestjs), NOT framework-neutral REST…
debug
Use when something is broken — a failing or flaky test, crash, wrong result or regression — and the root cause must be reproduced and proven before any fix. On-demand; callable mid-implement. NOT a feature to spec or build (that is specify/implement), NOT the lint/test gate (that is verify), NOT adversarial diff…
github-actions
Use when authoring or fixing GitHub Actions CI/CD — workflows under .github/workflows, triggers, job matrix, caching, token permissions, OIDC cloud deploys, environment gates, reusable workflows. NOT the Dockerfile or image build strategy (that is docker), NOT the branching model (that is git-workflow), NOT release…