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/rmarquesa/agentmemory-offline/agents-mdgit clone --depth 1 https://github.com/rmarquesa/agentmemory-offlineWhat 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 | $0.01546 | $0.01546 |
| Opus 5 | $0.00773 | $0.00773 |
| Sonnet 5 | $0.00309 | $0.00309 |
| Haiku 4.5 | $0.00155 | $0.00155 |
Grade A, and why
agentmemory-offline 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.
This is a copy
91% identical to agentmemory AGENTS.md — 12 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agentmemory — Agent Instructions
Architecture
agentmemory is a persistent memory system for AI coding agents, built on iii-engine's three primitives (Worker/Function/Trigger). Everything goes through registerFunction/registerTrigger/sdk.trigger() — never bypass iii-engine with standalone SQLite or in-process alternatives.
- Engine: iii-sdk (WebSocket to iii-engine on port 49134)
- State: File-based SQLite via iii-engine's StateModule (
./data/state_store.db) - Build: TypeScript → ESM via tsdown, output to
dist/ - Test: vitest (
npm testexcludes integration tests)
Consistency Rules
When adding or removing MCP tools, you MUST update ALL of the following:
src/mcp/tools-registry.ts— tool definition +getAllTools()arraysrc/mcp/server.ts— handler case in themcp::tools::callswitchsrc/triggers/api.ts— REST endpoint registrationsrc/index.ts— function registration + endpoint count in the log linetest/mcp-standalone.test.ts— tool count assertionREADME.md— tool counts (search for "MCP tools")plugin/.claude-plugin/plugin.json— tool count in descriptionplugin/plugin.jsonandplugin/.mcp.copilot.json(when present) — tool count or MCP exposure
When adding REST endpoints, you MUST update:
src/triggers/api.ts— endpoint registrationsrc/index.ts— endpoint count in the log lineREADME.md— endpoint count (search for "REST endpoints" and "endpoints on port")
When bumping version, you MUST update ALL of the following:
package.json— version fieldsrc/version.ts— VERSION constant and type unionsrc/types.ts— ExportData version unionsrc/functions/export-import.ts— supportedVersions settest/export-import.test.ts— version assertionplugin/.claude-plugin/plugin.json— version fieldplugin/plugin.json(when present) — version field
When adding new KV scopes:
src/state/schema.ts— add to the KV objectsrc/types.ts— add the corresponding interface
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 · 125 lines · 1,546 tokens per session scan A d39c24bec7ab
agentmemory-offline AGENTS.md is an instructions file published in the GitHub repository rmarquesa/agentmemory-offline (0 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,546 tokens to every session, about $0.0077 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to agentmemory AGENTS.md, differing in 12 lines, and is treated as a copy.
Other instructions, from other repositories
personal-model AGENTS.md
Instructions for Intuition-Lab/personal-model, covering agents.md, runtime boundary, commands, pipeline and documentation map.
plur CLAUDE.md
Instructions for plur-ai/plur, covering claude.md, what is plur, development, package dependency and version bumps.
personal-model CLAUDE.md
Instructions for Intuition-Lab/personal-model: Read and follow AGENTS.md. It is the single agent orientation for this repository: Runtime boundary, commands, architecture, invariants, current documentation, privacy rules, and DCO workflow.
engraphis AGENTS.md
Instructions for Coding-Dev-Tools/engraphis, covering agents.md — engraphis, 0. read this first — two architectures live in one package, 1. commands, ── unified dashboard + memory inspector ── and 2. the v2 recall pipeline (where the real work is).
paxm AGENTS.md
Instructions for pax-beehive/paxm, covering paxm 开发要求, git 与协作, 架构边界, 代码与验证 and 文档与发布.
brigade AGENTS.md
Instructions for escoffier-labs/brigade, covering agents.md, definition of done, rules, orientation and memory handoff.