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 agentmods add commands/habib0x0/spec-driven-plugin/spec-verifygit clone --depth 1 https://github.com/Habib0x0/spec-driven-pluginWhat 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 | $0.00014 | $0.00898 |
| Opus 5 | $0.00007 | $0.00449 |
| Sonnet 5 | $0.00003 | $0.00180 |
| Haiku 4.5 | $0.00001 | $0.00090 |
Grade A, and why
spec-verify 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 2d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/spec-verify Command
Run smoke tests against a deployed environment to verify the feature works in production/staging. Reuses the spec-tester agent with a target URL instead of localhost.
Philosophy
"It works on my machine" doesn't count. Post-deployment verification catches environment-specific issues: missing env vars, CORS misconfigs, database connectivity, CDN caching, etc. This is a lightweight check, not a full test suite — just enough to confirm the feature is alive.
Workflow
1. Locate the Spec
If a spec name is provided, use it. Otherwise auto-detect from .claude/specs/.
2. Get the Target Environment
If a URL was provided as a second argument, use it. Otherwise, ask via AskUserQuestion:
- Production — Enter the production URL
- Staging — Enter the staging URL
- Custom environment — Enter any URL
Also ask:
- Full smoke test — Verify all acceptance criteria that can be tested via browser
- Quick health check — Just verify the app loads and key routes respond
- Specific requirements — Pick which requirements to verify
3. Build the Smoke Test Plan
Read requirements.md and extract acceptance criteria that can be verified via browser/HTTP:
- UI behaviors → Playwright navigation and interaction
- API endpoints → HTTP requests to verify responses
- Authentication flows → Login/logout verification
- Error handling → Verify error pages/responses work
Skip criteria that require:
- Database state manipulation (unless safe read-only checks)
- Background job verification
- Internal-only metrics
4. Spawn the Tester Agent
Delegate to the spec-driven:spec-tester agent via the Task tool.
Pass the agent:
- The spec directory path
- The target URL (NOT localhost)
- The testing scope (full, quick, or specific)
- Instruction to treat this as a smoke test, not a full test suite — verify the feature exists and responds correctly, don't test every edge case
- Instruction to not modify any code or files — this is read-only verification
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.
- 2d ago First seen · 117 lines · 14 tokens per session scan A 462ac6581b7e
spec-verify is a command published in the GitHub repository Habib0x0/spec-driven-plugin (10 stars, last pushed 3mo ago), licensed MIT. It adds 14 tokens to every session and 898 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
generate-tests
Generate unit, integration, and e2e test suites from scaffolded project with framework-appropriate coverage.
agent-qa-automation-engineer
Dispatch hub:qa-automation-engineer — Specialist in test automation infrastructure and E2E testing.
e2e
使用 Playwright 对 Web UI 进行端到端测试（支持视频录制、Trace 录制、控制台/网络日志捕获）.
run-all-tests-and-fix
Execute the full test suite and systematically fix any failures, ensuring code quality and functionality. All test-related commands must pass before completion.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
fd-verify
Verify the implementation — run tests, check regression on affect.md files, review and scan; blocks /fd-done on failure.