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 instructions/mattgierhart/prd-driven-context-engineering/claude-mdgit 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/instructions/mattgierhart/prd-driven-context-engineering/claude-md)<a href="https://agentmods.dev/instructions/mattgierhart/prd-driven-context-engineering/claude-md"><img src="https://agentmods.dev/badge/instructions/mattgierhart/prd-driven-context-engineering/claude-md.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 | $0.00670 | $0.00670 |
| Opus 5 | $0.00335 | $0.00335 |
| Sonnet 5 | $0.00134 | $0.00134 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade A, and why
PRD-driven-context-engineering CLAUDE.md 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.
How it starts
The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Agent Operating Guide
Mission: Build software in lockstep with the PRD Version Lifecycle. Authority: Load
README.md→PRD.md→CLAUDE.md→ Active EPIC. Core Rule: If it's not in the ID Graph (Specs), it doesn't exist.
Rules are loaded automatically from .claude/rules/*.md.
Quick Reference
- Lifecycle Guide:
README.md - ID System:
SoT/SoT.UNIQUE_ID_SYSTEM.md - SoT Index:
SoT/SoT.README.md - EPIC Template:
epics/EPIC_TEMPLATE.md - Active Work:
epics/ - Domain Profile:
.claude/domain-profile.yaml - Hook Contract:
.claude/hooks/HOOK_CONTRACT.md - Agent Registry:
.claude/agents/ - Rules:
.claude/rules/ - SoT HTML Companion:
SoT/html/— human-review renders of each SoT file - Deliverables (concept):
docs/DELIVERABLES_CONCEPT.md— proposed input-mode layer where humans emit SoT markdown
SoT HTML Companion (when to use it)
The pages in SoT/html/ are for humans, not for context loading:
- Read: load the markdown SoT files for task context, never the HTML. The HTML duplicates markdown content in a heavier format — loading it wastes tokens.
- Write: when you add or change a SoT entry, mirror it in the companion page in the same
session — duplicate the matching
<article class="entry" id="PREFIX-XXX">block and fill the placeholders. Entry anchors must equal IDs; cross-references must bea.idhyperlinks. - Surface: at gate reviews, EPIC handoffs, or whenever a human asks to "see" the specs, point
them at
SoT/html/index.html(opens fromfile://, no build). - Extend: a new SoT file (via
ghm-sot-builder) gets a companion page — follow "Extending the library" inSoT/html/README.mdand register it inindex.html. - Conflict rule: if HTML and markdown disagree, markdown wins; fix the HTML.
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 · 46 lines · 670 tokens per session scan A 632b74c43717
PRD-driven-context-engineering CLAUDE.md is an instructions file published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 5d ago), licensed MIT. It adds 670 tokens to every session, about $0.0034 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 instructions, from other repositories
KDD AGENTS.md
AGENTS.md instructions for MauricioPerera/KDD: Este repositorio usa la metodología KDD (Knowledge-Driven Development). Las reglas obligatorias completas están en .agents/AGENTS.md y la skill local en .agents/skills/kdd-okf-ccdd-hybrid/SKILL.md.
nestjs-starter config.instructions.md
Instructions for hmake98/nestjs-starter: // src/app/config/redis.config.ts import { registerAs } from '@nestjs/config'.
nestjs-starter modules.instructions.md
Instructions for hmake98/nestjs-starter: @Module({ imports: [DatabaseModule], controllers: [PostPublicController, PostAdminController], providers: [PostService], exports: [PostService], }) export class PostModule {}.
AmbyKit CLAUDE.md
Claude Code instructions for ambystechcom/AmbyKit, covering claude code — notes for the ambykit repo and claude-specific.
lumen AGENTS.md
AGENTS.md instructions for ory/lumen, covering agents.md, repository expectations and commands.
eai-gofer GEMINI.md
Gemini CLI instructions for eai-support/eai-gofer, covering gemini.md and always-on eai contract.