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/govanai/mem-graph/agents-mdgit clone --depth 1 https://github.com/GoVanAI/mem-graphWhat 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 | $0.00811 | $0.00811 |
| Opus 5 | $0.00405 | $0.00405 |
| Sonnet 5 | $0.00162 | $0.00162 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
mem-graph 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 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.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mem-Graph Project Instructions for Codex
This file adds repository-specific routing to the global agent rules. It is a bootstrap contract, not a duplicate project-status document.
Use the repo-scoped $mem-graph-practice skill for any non-trivial mem-graph
or Cognitive OS task. The vendor-neutral source contract is
cognitive-os/agent-practice/practice.v1.json; generated host adapters must not
be edited by hand.
Scope
Cognitive OS is a global, cross-project agent framework. This repository is its current additive proving ground and persistence substrate; it is not the framework's architectural boundary. Canonical tracker and scope-boundary IDs are deployment-local and must come from operator or project configuration, not from this repository.
Keep scopes distinct:
- use
project_id=cognitive-osfor Cognitive OS governance, experiments, policies, event evidence, roadmap work, and program state; - use the applicable mem-graph project scope for substrate maintenance, releases, and unrelated runtime work; and
- never treat cross-project availability as automatic applicability.
Mandatory Cognitive OS Bootstrap
Before non-trivial Cognitive OS work:
- Prefer
cognitive_agent_bootstrapwithproject_id=cognitive-os, a narrow task query,include_canonical_content=true, andinclude_global=falseunless global guidance is explicitly required. Supplycanonical_idsonly when the operator or project has configured them; otherwise omit the field and use the governing lane to discover candidates. This tool is strictly read-only and does not touch access tracking or append a receipt. - Directly verify any candidate tracker, scope boundary, or role record before using it. When a canonical tracker is resolved, read the roadmap and active artifacts it references before changing implementation or making a milestone claim.
- Fetch selected known records directly when their full content or authority still needs verification.
- If the bootstrap tool is unavailable, use the dynamic fallback sequence:
resolve deployment-local canonical IDs from operator/project configuration
or exact-project governing guidance;
memory_geteach resolved record; then read referenced roadmap/artifacts and runcognitive_policy_lookupusingrequest_type/current_canonical_guidance, exact-projectcognitive_current_guidance_searchor diagnosis, and direct fetch of each selected record.
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 · 85 lines · 811 tokens per session scan A 181dd9cad35e
mem-graph AGENTS.md is an instructions file published in the GitHub repository GoVanAI/mem-graph (0 stars, last pushed 24d ago), licensed MIT. It adds 811 tokens to every session, about $0.0041 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
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).
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.
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.
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.
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).
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.