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-harvestgit 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-harvest)<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/ghm-harvest"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/ghm-harvest/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-harvest"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/ghm-harvest.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 | $0.00049 | $0.01170 |
| Opus 5 | $0.00024 | $0.00585 |
| Sonnet 5 | $0.00010 | $0.00234 |
| Haiku 4.5 | $0.00005 | $0.00117 |
Grade A, and why
ghm-harvest 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 10d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harvest
Extract durable insights from temporary files to Source of Truth during EPIC Phase E (Finish).
Workflow Overview
- Enumerate Temps → List all temp/ files from current EPIC
- Identify SoT-worthy → Determine what should persist
- Format Entries → Convert to proper SoT templates
- Archive → Move temps to archive, update manifest
Core Output Template
| Element | Definition | Evidence |
|---|---|---|
| Temp Files | Files processed | List with paths |
| New SoT Entries | IDs created | BR-XXX, UJ-XXX, etc. |
| Archive Manifest | What was archived | Paths and dates |
| Discarded | What was not kept | Reason for each |
Harvest Decision Matrix
| Content Type | Action | Destination |
|---|---|---|
| Business rule discovered | Extract | SoT/SoT.BUSINESS_RULES.md |
| User flow documented | Extract | SoT/SoT.USER_JOURNEYS.md |
| API design finalized | Extract | SoT/SoT.API_CONTRACTS.md |
| Customer feedback captured | Extract | SoT/SoT.customer_feedback.md |
| Session notes | Archive only | archive/YYYY-MM/ |
| Scratch work | Discard | Delete after review |
Step 1: Enumerate Temp Files
- Read EPIC Execution Plan for temp file references
- List all files in
temp/directory - Match temps to EPIC (by date or naming)
Checklist
- All EPIC-referenced temps identified
- Temp directory scanned
- Files categorized by content type
Step 2: Identify SoT-Worthy Content
For each temp file, evaluate:
| Question | If Yes | If No |
|---|---|---|
| Is this a business rule? | Extract as BR-XXX | Continue |
| Is this a user flow? | Extract as UJ-XXX | Continue |
| Is this an API design? | Extract as API-XXX | Continue |
| Is this customer evidence? | Extract as CFD-XXX | Continue |
| Is this useful context? | Archive | Continue |
| Is this scratch work? | Discard | - |
Checklist
- Each temp file evaluated
- Extract/Archive/Discard decision made
- Decisions documented
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.
- 10d ago First seen · 177 lines · 49 tokens per session scan A 104145f0142a
ghm-harvest is a skill published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 9d ago), licensed MIT. It adds 49 tokens to every session and 1,170 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
wiki
LLM Wiki — persistent markdown knowledge base that compounds across sessions (Karpathy model).
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
context-fundamentals
This skill should be used when the user asks to "understand context", "explain context windows", "design agent architecture", "debug context issues", "optimize context usage", or discusses context components, attention mechanics, progressive disclosure, or context budgeting. Provides foundational understanding of…
knowledge-steward
A knowledge-management helper that saves useful prompts, solutions, ideas, patterns, and workflow notes to an Obsidian knowledge base. Obsidian is a local app for organizing linked notes.
digital-brain
This skill should be used when the user asks to "write a post", "check my voice", "look up contact", "prepare for meeting", "weekly review", "track goals", or mentions personal brand, content creation, network management, or voice consistency.
moai-foundation-context
Manages context window optimization, session state persistence, and token budget allocation for multi-agent workflows. Use for token budget management, context limits, or session handoff across agents.