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/mnemon-dev/mnemon/agents-mdgit clone --depth 1 https://github.com/mnemon-dev/mnemonWhat 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 | $0.00611 | $0.00611 |
| Opus 5 | $0.00305 | $0.00305 |
| Sonnet 5 | $0.00122 | $0.00122 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
mnemon 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mnemon Agent Guidelines
Development
- Build the single product executable with
go build -o mnemon .. - Run
make testfor the deterministic CI suite. It excludes real daemon readiness, CLI E2E, wall-clock scenarios, Docker, and provider calls. - Run
make test-integrationexplicitly for CLI E2E plus Agency timing, race, process, and Docker boundaries; it is not a regular CI gate. - Run
make test-liveonly when explicitly validating the paid Pi/DeepSeek scenarios. - Treat
cmd/memoryandcmd/agencyas command namespaces within the singlemnemonexecutable. Keep existing Memory commands at the root; expose Agency throughmnemon agency ....mnemondremains the local daemon/protocol role, not a second executable. - Keep mnemond boundary suites under
test/mnemondand their data-only fixtures undertestdata/mnemond. - Treat
.claude/,.codex/,.openclaw/, and similar host directories as local projection surfaces, not canonical project state.
Go Engineering
- Read and follow the Go engineering standard before changing Go architecture, concurrency, durable state, or shared infrastructure.
- Use patterns, channels, generics, callbacks, and registries only when they
reduce sources of truth, state combinations, or modification points. They are
not usage quotas, and reducing
ifstatements or total lines is not a goal. - Keep authority, digest, fence, bounds, CAS cardinality, and fail-closed checks explicit. Every goroutine must have an owner, cancellation, bounded work, and a wait path.
- Preserve independent replay, crash, authorization, and race oracles while compressing fixtures and shared setup.
Commit Discipline
- Prefer small, logical commits. Split unrelated work instead of committing a broad mixed diff.
- Keep tightly coupled changes together when splitting would leave either commit misleading or incomplete.
- Use the project style already present in history: a concise Conventional Commit title plus one or two focused body paragraphs, with bullets only when they improve scanning.
- Choose the commit type by the primary project effect:
featfor new developer-facing or Agency capabilities.fixfor correctness repairs.testfor tests, eval scenarios, or fixtures that do not add a new reusable capability.docsfor documentation-only changes.refactorfor structure changes without intended behavior changes.chorefor repository hygiene and maintenance.
- Mention validation in the body when tests, evals, or manual checks are part of the work.
- Do not include agent attribution or co-author lines unless explicitly asked.
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 · 55 lines · 611 tokens per session scan A f371ed730b93
mnemon AGENTS.md is an instructions file published in the GitHub repository mnemon-dev/mnemon (540 stars, last pushed 9d ago), licensed Apache-2.0. It adds 611 tokens to every session, about $0.0031 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 2026-08-30.
Other instructions, from other repositories
agentic-context-engine AGENTS.md
Instructions for kayba-ai/agentic-context-engine, covering agents.md, repository guidelines, pipeline-first development (mandatory), core code protection and documentation maintenance.
graymatter AGENTS.md
Instructions for angelnicolasc/graymatter, covering agents.md, your tools, when to call which, first call and identity.
graymatter CLAUDE.md
Instructions for angelnicolasc/graymatter, covering claude.md, a user asked you to set graymatter up, you are working in a project that already uses graymatter and you are contributing to graymatter itself.
amfs CLAUDE.md
Instructions for raia-live/amfs, covering amfs memory — agent instructions, available mcp tools, identity, brain tools (agent-scoped) and shared knowledge tools.
wife AGENTS.md
Instructions for ma-nucho-pro/wife, covering if the user wants to install it, if the user wants to change something and rules that are not negotiable.
localmem-mcp CLAUDE.md
Instructions for OpenAgentHQ/localmem-mcp, covering claude.md, what this is, non-negotiables, layout and design decisions worth knowing.