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 skills/mattgierhart/prd-driven-context-engineering/skill_templatenpx skills add mattgierhart/PRD-driven-context-engineering --skill skill_templategit 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/skill_template)<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/skill_template"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/skill_template.svg" alt="Measured on agentmods" 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 | $0.00040 | $0.00584 |
| Opus 5 | $0.00020 | $0.00292 |
| Sonnet 5 | $0.00008 | $0.00117 |
| Haiku 4.5 | $0.00004 | $0.00058 |
Grade A, and why
prd-vXX-skill-name 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 5d 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
[Skill Name]
[One sentence summary of the skill's purpose.]
Workflow Overview
- Step 1 → Brief description
- Step 2 → Brief description
- Step 3 → Brief description
Core Output Template
[Define the primary output structure this skill produces]
| Element | Definition | Evidence |
|---|---|---|
| Field 1 | What this captures | How to validate |
| Field 2 | What this captures | How to validate |
See assets/output-template.md for copy-paste template.
Step 1: [First Major Step]
[Detailed instructions for this step]
Checklist
- Item 1
- Item 2
Step 2: [Second Major Step]
[Detailed instructions for this step]
Step 3: [Third Major Step]
[Detailed instructions for this step]
Quality Gates
Pass Checklist
- Gate 1: [Specific, measurable criterion]
- Gate 2: [Specific, measurable criterion]
- Gate 3: [Specific, measurable criterion]
Testability Check
- Can this output be validated?
- Does it reference IDs from SoT/?
How this is evaluated: This skill's output is scored by
scripts/readiness.py(a deterministic, $0, no-LLM proxy). Clearing a gate is permission to advance, not the goal — the goal is evidence. Padding inputs to move the score without moving the evidence is a frozen-replay defect. SeePRINCIPLES.mdP7.
Anti-Patterns
| Pattern | Example | Fix |
|---|---|---|
| Bad pattern 1 | "Example" | → "Better approach" |
| Bad pattern 2 | "Example" | → "Better approach" |
| Evidence fabrication | Back-filling confidence/evidence to clear a gate | → Cite a real source or mark the gap; never invent to pass (P4 anti-leakage, P7) |
Bundled Resources
references/[file].md— [Description of when to use]assets/[template].md— [Description of template purpose]
Handoff
[What happens after this skill completes? What stage/skill comes next?]
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.
- 5d ago First seen · 82 lines · 40 tokens per session scan A 89ff6dc15378
prd-vXX-skill-name is a skill published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 4d ago), licensed MIT. It adds 40 tokens to every session and 584 once invoked, about $0.0002 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.
nw-leanux-methodology
LeanUX backlog management methodology - user story template, story sizing, story states, task types, Definition of Ready/Done, anti-pattern detection and remediation.