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 prd-v07-epic-scopinggit 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/prd-v07-epic-scoping)<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/prd-v07-epic-scoping"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v07-epic-scoping/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/prd-v07-epic-scoping"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v07-epic-scoping.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 | $0.00128 | $0.04597 |
| Opus 5 | $0.00064 | $0.02299 |
| Sonnet 5 | $0.00026 | $0.00919 |
| Haiku 4.5 | $0.00013 | $0.00460 |
Grade A, and why
prd-v07-epic-scoping 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 — 457 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Epic Scoping
Position in workflow: v0.6 Technical Specification → v0.7 Epic Scoping → v0.7 Test Planning
Consumes
This skill requires prior work from v0.6 Technical Specification:
- API-* endpoint contracts (from v0.6 Technical Specification) — Endpoints define what must be built; API count signals complexity
- DBT-* data model specifications (from v0.6 Technical Specification) — Data entities and relationships inform natural boundaries
- ARC-* architecture decisions (from v0.6 Architecture Design) — System structure, module boundaries, and integration patterns define scoping boundaries
- FEA-* feature entries with MVP-SCOPE (from v0.3 Features Value Planning) — MVP boundary determines EPIC scope; post-MVP features defer to backlog
- Existing EPIC-* entries (if brownfield) — Inherited work packages constrain and sequence new EPICs
This skill assumes v0.6 Technical Specification is complete with API-/DBT- entries providing implementation contracts.
Produces
This skill creates/updates:
- EPIC-* entries (context-window-sized work packages, status-based) — Scope of work that fits in AI agent working memory with explicit dependencies, pre-load context budget, session state tracking, and acceptance criteria
- EPIC dependency graph — Sequencing showing which EPICs must complete before others; identifies infrastructure/foundation EPICs, critical path EPICs, and optional/secondary EPICs
- Context capsule specification — Pre-load checklist (SoT files, key IDs, code references) and working room estimate ensuring EPIC doesn't exceed 100k context tokens
All EPIC- entries are work package specifications, not confidence-based. They are:
- Sized for context windows (3-5 APIs, 2-4 DBT tables, 1-2 UJs, <100k pre-load tokens)
- Fully traceable (every EPIC references API-, DBT-, BR-, UJ-, TEST- from upstream)
- Sequenced explicitly (dependencies form a DAG; no circular dependencies)
- Deliverable-focused (measurable completion with acceptance criteria)
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 · 457 lines · 128 tokens per session scan A 2e466040b610
prd-v07-epic-scoping is a skill published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 9d ago), licensed MIT. It adds 128 tokens to every session and 4,597 once invoked, about $0.0006 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.