Borrowing it
Nothing to install: this file belongs to astragenie/astramem-local. 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/astragenie/astramem-local/main/AGENTS.mdgit clone --depth 1 https://github.com/astragenie/astramem-localWrote 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/astragenie/astramem-local/agents-md)<a href="https://agentmods.dev/instructions/astragenie/astramem-local/agents-md"><img src="https://agentmods.dev/badge/instructions/astragenie/astramem-local/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/astragenie/astramem-local/agents-md"><img src="https://agentmods.dev/badge/instructions/astragenie/astramem-local/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 | $0.01467 | $0.01467 |
| Opus 5 | $0.00733 | $0.00733 |
| Sonnet 5 | $0.00293 | $0.00293 |
| Haiku 4.5 | $0.00147 | $0.00147 |
Grade A, and why
astramem-local 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 8d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
astramem-local — Agent Instructions
Local-first, encrypted memory daemon for AI coding agents — hybrid retrieval (BM25 + vector + importance + freshness), provenance receipts, MCP tools, SQLCipher at rest. TypeScript + Node 20+
- Fastify + better-sqlite3 + sqlite-vec. Wire-compatible with astramem-plugin and the memory SaaS
backend. Full mission, architecture, and decisions:
CLAUDE.md.
Commands
Setup:
bun install
bun run build # tsc -p . -> dist/
Local dev (foreground, no OS service):
node dist/cli/index.js init # wizard: config.yaml + secrets.env, migrations, service, doctor
node dist/cli/index.js serve --port 7777 # foreground daemon
node dist/cli/index.js doctor # health checks
node dist/cli/index.js demo # 30s in-memory trial, seeded data, no Ollama required
Test:
bun run test # vitest run - includes the ADR-005 retrieval-eval gate (recall@10 >= 0.9, NDCG@10 >= 0.7)
bun run test:watch
bun run test:smoke # tests/smoke only
bun run test:soak # vitest.soak.config.ts
Contracts (wire-schema parity with the SaaS backend + astramem-plugin):
bun run contracts:generate # types + zod from contracts/schemas
bun run contracts:validate # node contracts/validate.mjs
Eval harnesses — read docs/eval-runs/README.md before quoting any number, every scored run
must be archived there:
bun run eval:locomo:sample / :run / :judge / :diagnose
bun run eval:longmemeval:sample / :smoke / :judge
bun run eval:extraction-bench
bun run perf:baseline
Structure
src/{audio,backup,budget,capture,cli,config,consolidate,contracts,distill,doctor,entity,
eval,ingest,log,mcp,memory-tool,pipeline,providers,proxy,recall,redact,search,
server,service,storage,sync,tag-hygiene,util,vector}/
contracts/ wire-schema source of truth - own package (generate-types/generate-zod/validate)
audio-addon/ astramem-audio - independently-versioned npm subpackage (FEAT-489 Slice B)
migrations/ sequential .sql files; embed dim + schema are single-sourced (see CLAUDE.md)
tests/ mirrors src/ layout + e2e, integration, smoke, soak, security
docs/ see docs/README.md for the full map
scripts/{eval,git-hooks,perf,spike,testbed}/ plus loose one-off scripts (gen-upgrade-fixture.mts, watch-daemon.ps1)
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.
- 8d ago First seen · 116 lines · 1,467 tokens per session scan A 5fd525ab84b0
astramem-local AGENTS.md is an instructions file published in the GitHub repository astragenie/astramem-local (0 stars, last pushed 3d ago), licensed MIT. It adds 1,467 tokens to every session, about $0.0073 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
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.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.