Borrowing it
Nothing to install: this file belongs to PCIRCLE-AI/memesh. 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/PCIRCLE-AI/memesh/main/AGENTS.mdgit clone --depth 1 https://github.com/PCIRCLE-AI/memeshWrote 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/pcircle-ai/memesh/agents-md)<a href="https://agentmods.dev/instructions/pcircle-ai/memesh/agents-md"><img src="https://agentmods.dev/badge/instructions/pcircle-ai/memesh/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/pcircle-ai/memesh/agents-md"><img src="https://agentmods.dev/badge/instructions/pcircle-ai/memesh/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 | $0.04383 | $0.04383 |
| Opus 5.5 | $0.01753 | $0.01753 |
| Sonnet 5.5 | $0.00877 | $0.00877 |
| Haiku 4.5 | $0.00438 | $0.00438 |
Grade A, and why
memesh 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 8d 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 — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using MeMesh — for AI agents
MeMesh gives local AI agents shared persistent memory. Hosts running as the
same user share ~/.memesh/knowledge-graph.db by default. MEMESH_DIR or
MEMESH_DB_PATH can select a different database; use matching settings when
hosts should share memories. Not installed yet? Follow
llms-install.md.
The loop that pays for itself
- Session start — load, don't re-explore. Call the
briefingtool once (CLI:memesh briefing) unless your host already injected the MeMesh memory block (Claude Code does, and so does the Codex plugin once Codex runs its hooks; see below). It returns the current project's work topology; read it instead of re-reading the repository to reconstruct context. The project's latest eligible handoff comes first, after optional repository facts: check its age and verify its claims against the files before acting on it. The rest depends on thebriefingsetting (memesh config set briefing <level>):minimal(default): this project — its decisions, lessons, knowledge and recent activity, with the repository state in front whenever anything else is shown — plus up to five of your memories that belong to no project (every level, under their own heading). No task state, no index, nothing from other projects. A project with nothing to show injects only the session's project line, and that line appears only when the host reports a usable working directory; without one there is no project line and nothing is guessed.standard: adds the stated goal / next / blocked / done when fresh, and a capped index of durable memories with[mem:id]handles (memesh briefing --indexprints just the index).full: adds other projects' recent activity and global memory. The SessionStart hook also appends a work-package notice atfull; that notice is an instruction to the host agent, not memory, andbriefingnever includes it.
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.
- 8d ago Changed · -17 tokens per session 7425de257d33
- 9d ago Changed · +1 tokens per session 0a13a2e34854
- 11d ago Changed · +1 lines · +16 tokens per session 55a8900965fe
- 21d ago Changed · +1 lines · +29 tokens per session 3c3c966ace1d
- 22d ago Changed · +13 lines · +261 tokens per session 91978cecd5b7
- 23d ago Changed · +4 lines · +62 tokens per session dcd6d2ee21d8
- 24d ago Changed · +6 lines · +142 tokens per session d392f31318cf
- 28d ago Changed · +4 lines · +78 tokens per session 488da4811123
- 29d ago Changed · +1 lines · +23 tokens per session dad547feb563
- 1mo ago First seen · 231 lines · 3,788 tokens per session scan A 18fadc019db2
memesh AGENTS.md is an instructions file published in the GitHub repository PCIRCLE-AI/memesh (16 stars, last pushed yesterday), licensed MIT. It adds 4,383 tokens to every session, about $0.0175 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.