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 mattgierhart/PRD-driven-context-engineering --skill ghm-id-registergit clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineeringWrote 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/mattgierhart/prd-driven-context-engineering/ghm-id-register)<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/ghm-id-register"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/ghm-id-register/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/mattgierhart/prd-driven-context-engineering/ghm-id-register"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/ghm-id-register.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00052 | $0.01626 |
| Opus 5 | $0.00026 | $0.00813 |
| Sonnet 5 | $0.00010 | $0.00325 |
| Haiku 4.5 | $0.00005 | $0.00163 |
Grade A, and why
ghm-id-register 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 9d 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ID Register
Validate and register new Source of Truth IDs with cross-reference integrity checks.
Workflow Overview
- Validate Format → Check ID follows
[PREFIX]-[3-digit]pattern - Check Uniqueness → Ensure ID doesn't already exist
- Verify Cross-Refs → All referenced IDs must exist
- Register Entry → Add to appropriate SoT file
Core Output Template
| Element | Definition | Evidence |
|---|---|---|
| ID | Unique identifier | BR-101, UJ-045, API-012 |
| Title | Short descriptive name | Clear, specific |
| Cross-References | Links to related IDs | All referenced IDs exist |
| Status | Current state | Draft / Active / Deprecated |
ID Format Reference
| Prefix | Domain | File |
|---|---|---|
BR- |
Business Rules | SoT/SoT.BUSINESS_RULES.md |
UJ- |
User Journeys | SoT/SoT.USER_JOURNEYS.md |
API- |
API Contracts | SoT/SoT.API_CONTRACTS.md |
CFD- |
Customer Feedback | SoT/SoT.customer_feedback.md |
Step 1: Validate Format
Check ID follows the pattern:
[PREFIX]-[XXX]
Where:
- PREFIX = BR, UJ, API, or CFD
- XXX = 3-digit number (zero-padded)
Checklist
- Prefix is valid (BR, UJ, API, CFD)
- Number is 3 digits
- Format matches
[A-Z]+-[0-9]{3}
Step 2: Check Uniqueness
- Read target SoT file
- Extract all existing IDs of same prefix
- Verify new ID doesn't exist
- If auto-assigning: use highest existing + 1
Checklist
- Target SoT file read
- Existing IDs enumerated
- New ID is unique
Step 3: Verify Cross-References
For each ID referenced in the new entry:
- Identify the prefix
- Check that ID exists in its SoT file
- Flag any missing references
Checklist
- All
BR-XXXreferences exist in BUSINESS_RULES - All
UJ-XXXreferences exist in USER_JOURNEYS - All
API-XXXreferences exist in API_CONTRACTS - All
CFD-XXXreferences exist in CUSTOMER_FEEDBACK - Each cross-reference includes a relationship type (see
references/cross-reference-patterns.md) - Relationship types match the directional hierarchy (vertical types for cross-layer, lateral types for same-layer)
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 198 lines · 52 tokens per session scan A 81f6e2ce77fa
ghm-id-register is a skill published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 9d ago), licensed MIT. It adds 52 tokens to every session and 1,626 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
ralplan
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution.
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
explaining-machine-learning-models
Explain trained machine learning models through feature attribution, local explanations, and behavior summaries. Use as an explicit/manual helper once a model already exists, not for training ownership, leakage auditing, or general ML strategy selection.
aiwg-regenerate-copilot
Regenerate copilot-instructions.md for GitHub Copilot with vendor-specific content only.