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.
git clone --depth 1 https://github.com/rjmurillo/ai-agentsWrote 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/commands/rjmurillo/ai-agents/spec-trace-requirements)<a href="https://agentmods.dev/commands/rjmurillo/ai-agents/spec-trace-requirements"><img src="https://agentmods.dev/badge/commands/rjmurillo/ai-agents/spec-trace-requirements/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/commands/rjmurillo/ai-agents/spec-trace-requirements"><img src="https://agentmods.dev/badge/commands/rjmurillo/ai-agents/spec-trace-requirements.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 | $0.00000 | $0.01424 |
| Opus 5.5 | $0.00000 | $0.00570 |
| Sonnet 5.5 | $0.00000 | $0.00285 |
| Haiku 4.5 | $0.00000 | $0.00142 |
Grade A, and why
spec-trace-requirements 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 today.
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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Requirements Traceability Check
You are verifying that implementation changes trace back to specification requirements.
Task
- Identify all requirements in the specification (look for REQ-*, acceptance criteria, user stories)
- For each requirement, determine if the implementation changes address it
- Report coverage status for each requirement
Identification Patterns
Look for requirements in these forms:
REQ-NNN: Formal requirement IDsDESIGN-NNN: Design specification IDsTASK-NNN: Task identifiersAC-Nor numbered acceptance criteria- User stories: "As a [user], I want [goal], so that [benefit]"
- Bullet points describing expected behavior
- "SHALL", "MUST", "SHOULD" statements (RFC 2119)
Coverage Status Definitions
COVERED: Implementation clearly addresses this requirementPARTIAL: Implementation partially addresses this requirementNOT_COVERED: No evidence that implementation addresses this requirementN/A: Requirement is not applicable to these changes
Output Format
Output your analysis in this format:
### Requirements Coverage Matrix
| Requirement | Description | Status | Evidence |
|-------------|-------------|--------|----------|
| REQ-001 | [brief description] | COVERED | [file:line or description] |
| REQ-002 | [brief description] | NOT_COVERED | - |
| REQ-003 | [brief description] | PARTIAL | [what's missing] |
### Summary
- Total Requirements: N
- Covered: N (X%)
- Partially Covered: N (X%)
- Not Covered: N (X%)
### Gaps
1. [Specific gaps or missing implementations]
End your analysis with a GitHub Alert block matching the verdict:
For PASS:
> [!TIP]
> **VERDICT: PASS**
> All requirements are covered by the implementation. [Brief explanation]
For PARTIAL:
> [!WARNING]
> **VERDICT: PARTIAL**
> Some requirements have gaps. [Brief explanation]
For FAIL:
> [!CAUTION]
> **VERDICT: FAIL**
> Critical requirements are not covered. [Brief explanation]
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.
- today First seen · 153 lines · 0 tokens per session scan A 5e81d7dbcb4e
spec-trace-requirements is a command published in the GitHub repository rjmurillo/ai-agents (48 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,424 tokens. 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 2026-10-19.
Other commands, from other repositories
review
When reviewing the code changes, the agent should apply general best practices to ensure high code quality. Key areas of evaluation include.
review-agent
Review one agent for standalone packaging, instruction quality, contradictory guidance, resource correctness, and current best practices.
review-instructions
Review one instruction file for applyTo glob accuracy, frontmatter conventions, overlap or conflict with sibling instructions and .github/copilot-instructions.md, and current best practices.
review-skill
Review one skill for standalone packaging, instruction quality, contradictory guidance, resource correctness, and current best practices.
review-workflow
Review one workflow folder for standalone packaging, Copilot customisation quality, local link correctness, and current best practices.
complexity
Forces the laziest solution that actually works — simplest, shortest, most minimal — on every coding task, and audits a diff, plan, or whole repo for over-engineering. Channel a lazy senior developer who has seen every over-engineered codebase and been paged at 3am for one: lazy means efficient, not careless, and the…