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/CLAUDE.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/claude-md)<a href="https://agentmods.dev/instructions/astragenie/astramem-local/claude-md"><img src="https://agentmods.dev/badge/instructions/astragenie/astramem-local/claude-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/claude-md"><img src="https://agentmods.dev/badge/instructions/astragenie/astramem-local/claude-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 | $0.02773 | $0.02773 |
| Opus 5 | $0.01386 | $0.01386 |
| Sonnet 5 | $0.00555 | $0.00555 |
| Haiku 4.5 | $0.00277 | $0.00277 |
Grade A, and why
astramem-local CLAUDE.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 9d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — astramem-local
@AGENTS.md
The include above is the tool-agnostic scaffold (commands, structure, style, credentials, never-do). Everything below is astramem-local-specific: mission, decisions an agent must not re-litigate, and where volatile state lives. This file changes rarely by design — dated facts, eval numbers, and open/closed incidents live in
docs/memory.md.
Session protocol — memory + issue tracing (mandatory, not advisory)
Before any non-trivial work (feature, fix, review, plan):
- Read
docs/memory.mdin full. It is the ONLY source for dated corrections, current LoCoMo/ eval numbers, known open gaps, and closed-incident records —CLAUDE.mddeliberately contains none of that. Skipping it means working on stale assumptions (this file itself used to embed that state directly; the 2026-07-21 rebuild extracted it for exactly this reason). - Re-verify before relying.
docs/eval-runs/LEDGER.mdnumbers anddocs/memory.md's dated bullets are a cache, not the truth — re-check against the cited source (a test file, a config constant, a migration) before quoting either in a decision. - Write-back is part of the task. Any fact you verify, any number that moved, any incident
that closed: update
docs/memory.mdin the same session — supersede the entry in place and refresh its date. A session that learns something and doesn't write it back is a defect.
Mission
astramem-local is a local-first memory daemon for AI coding agents — it captures every Claude
Code session transcript, distills typed memories (decisions, facts, lessons, commands, todos)
through an 8-stage pipeline, and serves them back via hybrid search, entirely on the user's
workstation with no cloud account required. It is wire-compatible with the astramem-plugin
Claude Code plugin and the memory SaaS backend (shared atom/retrieval/capture/sync contracts). Per
the kb strategy research, astramem-local is the flagship product the company is built around
(see ../kb/12-research/astra-strategy-2026-07/README.md, machine-local path).
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.
- 9d ago First seen · 139 lines · 2,773 tokens per session scan A 65c7aa5f6497
astramem-local CLAUDE.md is an instructions file published in the GitHub repository astragenie/astramem-local (0 stars, last pushed 4d ago), licensed MIT. It adds 2,773 tokens to every session, about $0.0139 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).
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.
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.