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 wedabro/bro-skills --skill speckit.checkergit clone --depth 1 https://github.com/wedabro/bro-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/wedabro/bro-skills/speckit.checker)<a href="https://agentmods.dev/skills/wedabro/bro-skills/speckit.checker"><img src="https://agentmods.dev/badge/skills/wedabro/bro-skills/speckit.checker/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/wedabro/bro-skills/speckit.checker"><img src="https://agentmods.dev/badge/skills/wedabro/bro-skills/speckit.checker.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 | $0.00027 | $0.00323 |
| Opus 5.5 | $0.00011 | $0.00129 |
| Sonnet 5.5 | $0.00005 | $0.00065 |
| Haiku 4.5 | $0.00003 | $0.00032 |
Grade A, and why
speckit.checker 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 1mo 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.
What it actually says
Mission
Detect actionable code, configuration, security, and performance risks using checks supported by the actual project.
Inputs and Outputs
- Read source, manifests, constitution, project config, Docker files, and documented commands.
- Write
.agents/memory/checker-report.mdwith command, scope, timestamp, findings, and N/A reasons.
Protocol
- Discover language, package manager, framework, services, containerization, and available formatter/type/lint/test/build commands.
- Build an applicability matrix. Run every applicable check; mark unavailable checks N/A with reason, never PASS.
- Run compile/type/lint and configured tests in Docker when required. Capture exit code and bounded output.
- Validate Compose config, Docker COPY paths, non-root runtime, health checks, ENV ports, dependency lockfiles, and production mounts when applicable.
- Scan tracked source for secrets, unsafe URLs, injection sinks, unsafe HTML/eval, SQL concatenation, and dependency risks; redact values and exclude generated/vendor paths.
- Apply stack-specific checks only after detection and report file plus line for each finding. Classify Critical/High/Medium/Low/Info.
Completion Gate
The report names every applicable check, evidence command, result, and remaining limitation. Any Critical finding yields FAIL.
Guard Rails
Read-only. Do not edit code or hide failures. Do not flag intentional documentation URLs as secrets without evidence.
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.
- 1mo ago Changed · -50 lines · +8 tokens per session 2e8a80376b01
- 1mo ago First seen · 75 lines · 19 tokens per session scan A c9ac1b68a5c1
speckit.checker is a skill published in the GitHub repository wedabro/bro-skills (3 stars, last pushed 13d ago), licensed MIT. It adds 27 tokens to every session and 323 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
windbg-kernel-bugcheck-triage
Use when a kernel dump reports a Windows bugcheck; decode parameters and recover exception or trap context before investigating your driver. Not for user-mode process crashes or blaming a module from its name alone.
windbg-user-exception-triage
Use when a native C/C++ app, service, or user-mode driver host (including UMDF) crashes with a structured exception in a dump or WinDbg session, including native faults inside managed processes. Not for managed .NET exceptions, WinUI/XAML app errors, or kernel bugchecks.
windbg-user-virtual-memory-exhaustion
Use when a native app, service, or user-mode driver host allocation fails; distinguish VA exhaustion, fragmentation, and commit pressure. Not for managed .NET heap growth, proving a leak from one snapshot, or corruption.
windbg-kernel-lock-deadlock-triage
Use when kernel threads block on driver synchronization or Verifier reports a lock-order violation; build an owner/waiter graph. Not for treating every watchdog stop as a deadlock or listing every lock type with !locks.
windbg-user-mutex-held-across-co-await
Use when app, service, or user-mode driver C++ coroutine code holds a thread-affine lock across suspension and later hangs or fails. Not for all coroutine crashes or choosing lock performance.
agent-incident-postmortem
Run a blameless postmortem for an incident caused by an AI agent or LLM feature — hallucinated facts shipped to users, runaway tool use, prompt injection, cost blowouts, or wrong actions taken autonomously. Use when asked to write up an AI incident, analyse why an agent did something wrong, or produce corrective…