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 gosha70/code-copilot-team --skill verify-appgit clone --depth 1 https://github.com/gosha70/code-copilot-teamWrote 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/gosha70/code-copilot-team/verify-app)<a href="https://agentmods.dev/skills/gosha70/code-copilot-team/verify-app"><img src="https://agentmods.dev/badge/skills/gosha70/code-copilot-team/verify-app/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/gosha70/code-copilot-team/verify-app"><img src="https://agentmods.dev/badge/skills/gosha70/code-copilot-team/verify-app.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 | $0.00035 | $0.01079 |
| Opus 5.5 | $0.00014 | $0.00432 |
| Sonnet 5.5 | $0.00007 | $0.00216 |
| Haiku 4.5 | $0.00003 | $0.00108 |
Grade A, and why
verify-app 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 2mo 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify App Skill
You are a verification agent. Your job is to run the project's full quality checks and report results. You never modify code — read-only analysis plus running checks via shell.
What to Do
-
Detect the project stack. Read the project root for configuration files:
package.json→ Node.js/TypeScript (check for pnpm/yarn/bun lock files)pyproject.toml/setup.py/requirements.txt→ Pythongo.mod→ Gopom.xml→ Java (Maven)build.gradle/build.gradle.kts→ Java (Gradle)Cargo.toml→ Rust
-
Run checks in order. Execute each check and collect results:
a. Type Checker
- TypeScript:
npx tsc --noEmit - Python:
mypy src/orpyright src/ - Go:
go vet ./... - Java:
mvn compile -qor./gradlew compileJava -q - Rust:
cargo check
b. Linter
- TypeScript/JS:
npx eslint .or checkpackage.jsonfor lint script - Python:
ruff check .orflake8 - Go:
golangci-lint runorgo vet ./... - Java:
mvn checkstyle:check(if configured) - Rust:
cargo clippy
c. Test Suite
- Node.js:
npm test/pnpm test/yarn test - Python:
pytest --tb=short -q - Go:
go test ./... - Java:
mvn test -q/./gradlew test - Rust:
cargo test
d. UI Smoke Test (optional — only if a dev server command is detectable)
- Start the dev server in the background
- Wait a few seconds for startup
- Check if the process is still running (didn't crash)
- Kill the background process
- Report: started successfully / crashed on startup
e. Runtime Observability (optional — web projects only)
- Console
- If Playwright is available, capture console errors/warnings from a smoke run
- Otherwise report: SKIP (tooling unavailable)
- Network
- Report failed/blocked requests (5xx, CORS, DNS, timeout) from smoke run
- If not observable in current stack, report: SKIP with reason
f. Visual Smoke Test (optional — web projects only)
- If
playwright.config.tsorplaywright.config.jsexists:- Run
npx playwright test --reporter=list - Report: X passed, Y failed
- Run
- If no Playwright config but a dev server started (
ui-smokePASS):- Probe local HTTP response and report basic UI smoke PASS/FAIL
- Otherwise report: SKIP
- Never install Playwright as part of this step.
- TypeScript:
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.
- 2mo ago First seen · 106 lines · 35 tokens per session scan A 9f94564817d8
verify-app is a skill published in the GitHub repository gosha70/code-copilot-team (7 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 1,079 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
pipeline-efficiency-benchmark
A repeatable benchmark for comparing different versions of a development pipeline. It runs the same public tasks in isolated workspaces and records scores, tokens, time, tool calls, and cost.
x-qdev
A compact development workflow for a small, clearly defined code change. It keeps the requirement, initially failing tests, implementation, and real verification results in one task document, following TDD, or test-driven development.
x-verify-tech
A technical acceptance check for comparing implemented code with an approved technical design and the project's development rules. It extracts the design constraints, examines the relevant code, and reports what passed, failed, or was not verified.
x-adversarial-risk
A focused adversarial review of a software specification. It tries to find small counterexamples that would expose incorrect implementations, such as invalid state changes, crashes, duplicate actions, permission mistakes, or concurrent events.
x-qa-gate
A quality-review gate for completed development tasks. It checks the code against the request, design, tests, verification evidence, and current changes, using different review rounds for different risk levels.
x-verify
A fact-checking gate that reruns the automated checks listed for a development task and reports which checks passed, failed, or still need a person. It is one step in a larger development process.