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/dongtang3/mnemic/agents-mdgit clone --depth 1 https://github.com/dongtang3/mnemicWrote 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/dongtang3/mnemic/agents-md)<a href="https://agentmods.dev/instructions/dongtang3/mnemic/agents-md"><img src="https://agentmods.dev/badge/instructions/dongtang3/mnemic/agents-md.svg" alt="Measured on agentmods" 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 | $0.00221 | $0.00221 |
| Opus 5 | $0.00111 | $0.00111 |
| Sonnet 5 | $0.00044 | $0.00044 |
| Haiku 4.5 | $0.00022 | $0.00022 |
Grade A, and why
mnemic 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 3d 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
Mnemic Agent Instructions
Mnemic is a graph-backed long-term memory substrate for coding agents and LLM applications.
When the mnemic_* MCP tools are available:
- Start non-trivial work by calling
mnemic_context_packwith the current task and a concrete project scope. - For broad or fresh sessions, call
mnemic_session_briefingbefore making implementation decisions. - Store a memory with
mnemic_rememberfor durable architecture decisions, reusable bug fixes, release or environment rules, recurring workflows, and project-specific constraints. - Use stable
sourceKeyvalues when possible, such as commit SHAs, issue IDs, ticket IDs, or session-summary IDs, so repeated runs update rather than duplicate memory. - Set
confidencebelow1.0when a memory is inferred, external, temporary, or likely to go stale. - Keep memories factual, searchable, scoped to a project, and free of secrets.
If the MCP server is unavailable, continue normally and mention that Mnemic memory was not reachable.
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.
- 3d ago First seen · 15 lines · 221 tokens per session scan A 543e5867dcfb
mnemic AGENTS.md is an instructions file published in the GitHub repository dongtang3/mnemic (0 stars, last pushed 21d ago), licensed MIT. It adds 221 tokens to every session, about $0.0011 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
trinity AGENTS.md
AGENTS.md instructions for trinity-tick/trinity, covering agents.md — trinity memory, trinity 记忆层实时快照（生成于 2026-09-02 03:21:12，snapshot 任务自动刷新）, 活跃目标（active goals）, 最近会话（recent sessions） and 1. trinity 是什么.
engraphis AGENTS.md
AGENTS.md instructions for Coding-Dev-Tools/engraphis, covering agents.md — engraphis, internal subagent delegation, 0. read this first — two architectures live in one package, 1. commands and ── unified dashboard + memory inspector ──.
Agent-Memory-Bridge AGENTS.md
Instructions for zzhang82/Agent-Memory-Bridge, covering agent memory bridge contributor instructions, setup and checks, architecture boundaries, mutation and migration invariants and benchmark expectations.
agentmemory-codex-windows AGENTS.md
Instructions for M-T-D-N/agentmemory-codex-windows, covering agentmemory — agent instructions, architecture, windows/codex downstream profile, consistency rules and code patterns.
cli AGENTS.md
Instructions for konteks/cli, covering agent instructions, project overview, tech stack, repository layout and common commands.
Crux AGENTS.md
Instructions for CueCrux/Crux, covering agents.md, reading order (start here), verify the claims yourself (do not trust this file), the 60-second trust-core tour and build / test.