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/chirino/memory-service/agents-mdgit clone --depth 1 https://github.com/chirino/memory-serviceWhat 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 | $0.05005 | $0.05005 |
| Opus 5 | $0.02502 | $0.02502 |
| Sonnet 5 | $0.01001 | $0.01001 |
| Haiku 4.5 | $0.00500 | $0.00500 |
Grade A, and why
memory-service 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.
How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Service
A memory service for AI agents that stores messages exchanged with LLMs and users, supporting conversation replay and forking.
Self-Updating Knowledge:
When you discover something meaningful about this project during your work—architecture patterns, naming conventions, gotchas, dependency quirks, correct/incorrect assumptions in existing docs — update AGENTS.md (or the relevant skill file) immediately so future sessions benefit without re-discovering it. Specifically:
- Correct any skill or doc content you find to be outdated or wrong.
- Refine trigger criteria in skill descriptions if a skill was loaded but wasn't relevant to the task—tighten its description so it activates more precisely.
- Keep updates concise and factual. Don't bloat files with obvious or generic information.
- Module specific knowlege should be placed into a
FACTS.mdin the top level directory of that module to avoid poluting AGENTS.md
Key Concepts
- Agent apps mediate all operations: Agent apps are the primary consumers. They sit between end users and the memory service, mediating all interactions.
- Agent API: For agent apps - manage conversations, append entries, retrieve context for LLMs. Some agent APIs are designed to be safely exposed to frontend apps (e.g., SPAs) for features like listing conversations, semantic search, viewing messages, and forking.
- Admin API: For administrative operations and system management.
- User access control: Conversations are owned by users with read/write/manager/owner access levels.
- Data stores: PostgreSQL, MongoDB; Redis, Infinispan (caching); PGVector, Qdrant (vector search).
- Porting Server To Go: we are porting the ./memory-service java module to ./main.go
- dev mode:
task dev:memory-serviceruns the go-based memory service using air for hot reloading on port 8082 and it's dependencies get started with docker compose. - Local developer tooling policy:
compose.yamlandtask dev*prioritize zero-configuration ease of use over production security hardening; keep demo credentials and avoid mandatory secret-generation setup. Embedded MCP has the same single-user desktop assumption.
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 · 144 lines · 5,005 tokens per session scan A 6c0689500370
memory-service AGENTS.md is an instructions file published in the GitHub repository chirino/memory-service (11 stars, last pushed 6d ago), licensed Apache-2.0. It adds 5,005 tokens to every session, about $0.0250 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
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.