Borrowing it
Nothing to install: this file belongs to MnemeHQ/mneme. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/MnemeHQ/mneme/main/AGENTS.mdgit clone --depth 1 https://github.com/MnemeHQ/mnemeWrote 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/mnemehq/mneme/agents-md)<a href="https://agentmods.dev/instructions/mnemehq/mneme/agents-md"><img src="https://agentmods.dev/badge/instructions/mnemehq/mneme/agents-md/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/instructions/mnemehq/mneme/agents-md"><img src="https://agentmods.dev/badge/instructions/mnemehq/mneme/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00379 | $0.00379 |
| Opus 5.5 | $0.00152 | $0.00152 |
| Sonnet 5.5 | $0.00076 | $0.00076 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
mneme 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 1mo 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.
What it actually says
AGENTS.md
Notes for AI agents working in this repository.
Repository workflow, worktree lifecycle, merge policy, and architecture constraints are defined in CLAUDE.md; those rules apply regardless of which agent is executing the task.
Agent execution provenance
Every pull request must record who actually produced the change. Git author identity is not sufficient because agent work is commonly committed under the human owner's Git identity.
Use the PR template's Execution provenance block. Required fields:
Change author:human,agent, ormixed.Agent: the concrete agent surface (codex,claude-code,kiro,chatgpt-work, etc.), ornonefor human-only work.Agent model: model identifier when exposed;not-exposedis acceptable when the tool does not expose it;n/aonly for human-only work.Agent session: stable session ID or share/work URL when available;not-exposedis acceptable when unavailable;n/aonly for human-only work.Task origin: where the task was scoped (chatgpt,claude,local,manual, etc.).Human owner: GitHub username responsible for review/promotion.
When an agent creates commits directly, also append commit trailers where practical:
Agent: codex
Agent-Model: gpt-5.6-sol
Agent-Session: cx_...
Task-Origin: chatgpt
Human-Owner: TheoV823
The PR body is the durable source of truth because squash merges may collapse or discard individual commit trailers.
Authorship, human promotion, release/deployment, and worktree cleanup are separate lifecycle facts. Never infer one from another. If usage/session limits interrupt the task, report the remaining lifecycle step explicitly.
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.
- 1mo ago First seen · 33 lines · 379 tokens per session scan A 2ef4e85f3f8f
mneme AGENTS.md is an instructions file published in the GitHub repository MnemeHQ/mneme (29 stars, last pushed today), licensed MIT. It adds 379 tokens to every session, about $0.0015 per session on Opus 5.5. 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
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
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, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.