Borrowing it
Nothing to install: this file belongs to chirino/memory-service. 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/chirino/memory-service/main/AGENTS.mdgit clone --depth 1 https://github.com/chirino/memory-serviceWrote 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/chirino/memory-service/agents-md)<a href="https://agentmods.dev/instructions/chirino/memory-service/agents-md"><img src="https://agentmods.dev/badge/instructions/chirino/memory-service/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/chirino/memory-service/agents-md"><img src="https://agentmods.dev/badge/instructions/chirino/memory-service/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 | $0.00913 | $0.00913 |
| Opus 5.5 | $0.00365 | $0.00365 |
| Sonnet 5.5 | $0.00183 | $0.00183 |
| Haiku 4.5 | $0.00091 | $0.00091 |
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 1mo 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 — 39 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.
Recording knowledge
Record something only if it caused a real failure or wasted significant time, and a future session couldn't learn it from the code, tests, contracts (contracts/), or site docs. Most discoveries don't qualify. When one does, use the first destination that fits:
- Test: an invariant a test can enforce, including site doc tests for what the docs must say.
- Code comment at the code the gotcha is about. Keep it short.
- Skill (
.skills/<name>/SKILL.md): a multi-step procedure. Itsdescriptionmust name the files or tasks that should trigger it. - This file: only a cross-cutting trap that most sessions need and that has no code location. One or two lines.
Don't copy contract details (endpoints, enum values, field semantics) into prose; point to the contract. Don't record what a file contains, what changed, or future plans. If you find a record here, in a skill, or in a comment that's wrong, fix or delete it in the same change. If a skill loaded but wasn't relevant, tighten its description.
Key concepts
- Agent apps sit between end users and the memory service and mediate all operations. The Agent API serves them, and some of its operations are safe to expose to frontends such as SPAs. The Admin API is for administration.
contracts/holds the OpenAPI (contracts/openapi/) and protobuf (contracts/protobuf/) sources of truth.- Local developer tooling (
compose.yaml,task dev*, embedded MCP) favors zero-configuration ease of use over production hardening. Keep demo credentials and don't add mandatory secret-generation steps.
Commands
task dev:memory-serviceruns the Go service with Air hot reload on port 8082 and starts its dependencies with Docker Compose.- The Maven wrapper and reactor root are under
java/. From the repo root, run./java/mvnw -f java/pom.xml .... - Verify each change with the checks for the modules you touched. The
build-testskill lists them.
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.
- 1mo ago Changed · -109 lines · -4,544 tokens per session e9fde1d577bc
- 1mo ago Changed · +1 lines · +89 tokens per session 2be079571a00
- 1mo ago Changed e8fe4d6bf6b5
- 1mo ago Changed · +2 lines · +123 tokens per session 1cad59b114a1
- 1mo ago Changed · +3 tokens per session 1e282f0017c5
- 1mo ago Changed · +1 lines · +105 tokens per session f0af284374ac
- 1mo ago Changed · +132 tokens per session 55906835355d
- 2mo 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 (12 stars, last pushed yesterday), licensed Apache-2.0. It adds 913 tokens to every session, about $0.0037 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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.