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/allenmaxi/contextgraph/claude-mdgit clone --depth 1 https://github.com/AllenMaxi/ContextGraphWhat 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 | $0.00538 | $0.00538 |
| Opus 5 | $0.00269 | $0.00269 |
| Sonnet 5 | $0.00108 | $0.00108 |
| Haiku 4.5 | $0.00054 | $0.00054 |
Grade A, and why
ContextGraph 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 2d 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.
This is a copy
94% identical to OpenAIWorkshop copilot-instructions.md — 109 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
1. Plan Mode Default
-Always use caveman as skill.
- Enter plan mode for ANY non-trivial task (3+ steps or architectural decisions)
- If something goes sideways, STOP and re-plan immediately - don't keep pushing
- Use plan mode for verification steps, not just building
- Write detailed specs upfront to reduce ambiguity
2. Subagent Strategy
- Use subagents liberally to keep main context window clean
- Offload research, exploration, and parallel analysis to subagents
- For complex problems, throw more compute at it via subagents
- One task per subagent for focused execution
3. Self-Improvement Loop
- After ANY correction from the user: update
tasks/lessons.mdwith the pattern - Write rules for yourself that prevent the same mistake
- Ruthlessly iterate on these lessons until mistake rate drops
- Review lessons at session start for relevant project
4. Verification Before Done
- Never mark a task complete without proving it works
- Diff behavior between main and your changes when relevant
- Ask yourself: "Would a staff engineer approve this?"
- Run tests, check logs, demonstrate correctness
5. Demand Elegance (Balanced)
- For non-trivial changes: pause and ask "is there a more elegant way?"
- If a fix feels hacky: "Knowing everything I know now, implement the elegant solution"
- Skip this for simple, obvious fixes - don't over-engineer
- Challenge your own work before presenting it
6. Autonomous Bug Fixing
- When given a bug report: just fix it. Don't ask for hand-holding
- Point at logs, errors, failing tests - then resolve them
- Zero context switching required from the user
- Go fix failing CI tests without being told how
Task Management
- Plan First: Write plan to
tasks/todo.mdwith checkable items - Verify Plan: Check in before starting implementation
- Track Progress: Mark items complete as you go
- Explain Changes: High-level summary at each step
- Document Results: Add review section to
tasks/todo.md - Capture Lessons: Update
tasks/lessons.mdafter corrections
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.
- 2d ago First seen · 59 lines · 538 tokens per session scan A 796d059b12c0
ContextGraph CLAUDE.md is an instructions file published in the GitHub repository AllenMaxi/ContextGraph (21 stars, last pushed 4mo ago), licensed MIT. It adds 538 tokens to every session, about $0.0027 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to OpenAIWorkshop copilot-instructions.md, differing in 109 lines, and is treated as a copy.
Other instructions, from other repositories
m_flow AGENTS.md
AGENTS.md instructions for FlowElement-xinliuyuansu/m_flow, covering m-flow — developer & agent reference, 1. repository map, extension points, 2. local development and python backend (requires python 3.10 – 3.13).
engraphis AGENTS.md
Instructions for Coding-Dev-Tools/engraphis, covering agents.md — engraphis, 0. read this first — two architectures live in one package, 1. commands, ── unified dashboard + memory inspector ── and 2. the v2 recall pipeline (where the real work is).
engraphis CLAUDE.md
Instructions for Coding-Dev-Tools/engraphis, covering claude.md, the one rule that prevents most mistakes, before you say "done" — run the canonical gate, slash commands available here and working style in this repo.
Waggle-mcp AGENTS.md
Instructions for Abhigyan-Shekhar/Waggle-mcp, covering repository agent rules, custom rules and waggle automatic memory.
Core-Memory CLAUDE.md
Instructions for JohnnyFiv3r/Core-Memory, covering claude.md — core memory, what this repo is, guiding principle — engineering simplicity, boring primitives, rich views and mapping to the current codebase.
engram-mcp CLAUDE.md
Instructions for edg-l/engram-mcp, covering engram mcp, development rules, structure, key types and mcp capabilities.