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/snowlightpath/extended-mind/agents-mdgit clone --depth 1 https://github.com/SnowLightPath/extended-mindWhat 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 | $0.01258 | $0.01258 |
| Opus 5 | $0.00629 | $0.00629 |
| Sonnet 5 | $0.00252 | $0.00252 |
| Haiku 4.5 | $0.00126 | $0.00126 |
Grade A, and why
extended-mind AGENTS.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 yesterday.
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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extended Mind
Protocol
→ DDL-PROTOCOL
→ Read .Codex/commands/DDL-PROTOCOL-SKILL.md before executing any command
Commands
| Command | Intent |
|---|---|
/draft |
Write the user-side experience first |
/realize |
Write code based on design principles |
/reflect |
Update documents based on implementation |
/commit |
Git commit |
/docs |
Audit and fix documentation |
/refactoring |
Audit and fix code quality |
Structure
design.md- Design Document (PCP detailed specification)seed/core.yaml- Initial core context (human identity + ontology)seed/active.template.json- Initial active context template (work state)
Detection Targets
Every command defines its own D1–D7. Cross-cutting targets below apply globally.
+++DETECT: G1: Vague Intent — Task description lacks measurable outcome G2: Scope Creep — Change touches files outside stated scope G3: Principle Violation — Action contradicts design.md principles G4: Missing Validation — No verification step after mutation G5: Leaked Specifics — Project-specific paths/commands hardcoded in framework files G6: Silent Failure — Error swallowed without user notification G7: Unreviewed Mutation — Shared artifact changed without +++STOP G8: Compression Violation — put() message rewritten or restructured by server G9: Core Write Violation — AI client writes to core layer
Behavior
On session start
- Read
AGENTS.md(this file) - Read
design.mdif it exists — extract scopes, principles, validation commands - If Extended Mind MCP is configured and
EM_ENABLEDenv var is set: callcontext_get()
On any task
- Identify which scopes (from
design.md) are affected - Run the command's Phase sequence
- Scan for Detection Targets at each phase boundary
On completion
- Summarize what changed (files, lines, scopes)
- List any Detection Targets that fired
- Suggest next command if applicable (
/draft→/realize→/reflect) - If
EM_ENABLEDand significant decisions: callcontext_log()via Extended Mind
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.
- yesterday First seen · 133 lines · 1,258 tokens per session scan A e43645d7a900
extended-mind AGENTS.md is an instructions file published in the GitHub repository SnowLightPath/extended-mind (1 stars, last pushed 5mo ago), licensed MIT. It adds 1,258 tokens to every session, about $0.0063 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 2026-08-31.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.