What is AgentRecall CLAUDE.md?

Project instructions for AgentRecall, which contains two related applications in one repository. They describe setup, development, testing, type checking, release-note checks, packaging checks and how the shared architecture affects both applications.

Use them when developing either app, running focused or full tests, checking types, preparing releases, validating packages, or making changes shared by both versions.

They show a coding agent how to install and test the repository safely and which checks are required before a merge request. This helps avoid changing one application while missing its counterpart.

AgentRecall CLAUDE.md — Instructions file for coding agents by zszz3: Project instructions for AgentRecall, which contains two related appli

Install

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.

agentmods

npx agentmods add instructions/zszz3/agentrecall/claude-md

Clone the repo

git clone --depth 1 https://github.com/zszz3/AgentRecall

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/zszz3/agentrecall/claude-md.svg)](https://agentmods.dev/instructions/zszz3/agentrecall/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/zszz3/agentrecall/claude-md"><img src="https://agentmods.dev/badge/instructions/zszz3/agentrecall/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 3,373 This file is loaded in full into every session.

When invoked 3,373 The same file — it is already loaded in full.

Security scan B 1 finding. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.03373	$0.03373
Opus 5	$0.01687	$0.01687
Sonnet 5	$0.00675	$0.00675
Haiku 4.5	$0.00337	$0.00337

Measured 6d ago against content hash 44990f3aa674, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade B, and why

AgentRecall CLAUDE.md scanned grade B with 1 finding 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 6d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- **`bin/*.cjs` are dependency-free CommonJS with no build output** (launcher, self-updater, statusline, session-sync and memory hooks, MCP setup). They must work straight out of a global npm install, are idempotent and

CLAUDE.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Also read AGENTS.md — it holds the binding rules for release notes, dual-app changes, merge/versioning, and safe test practices. This file covers commands and architecture.

Commands

npm run setup                # setup:v1 + setup:v2 (do this instead of npm install — see below)
npm run dev:v1               # or dev:v2
npm test                     # test:repo + test:v1 + test:v2
npm run typecheck            # tsc --noEmit in both apps
npm run release-note:check   # MUST pass before opening an MR
npm run package:smoke:all    # build + tarball-install smoke for both apps, in parallel

Per-app work is faster scoped:

npm --prefix apps/main-2.0 test        # vitest run && node --test scripts/*.test.mjs
cd apps/main-2.0 && npx vitest run src/core/postgres/schema.test.ts   # single file
cd apps/main-2.0 && npx vitest run -t "reconciles the OpenViking"     # single test by name
cd apps/main-1.0 && npx vitest         # watch mode
npm run test:workflow-transaction    # V2 workflow-v2 / workspace-transaction gate
npm run test:workflow-performance    # V2 incremental-IPC regression gate

Notes:

npm install alone is not enough. scripts/setup-app.mjs runs npm ci with AGENT_RECALL_SKIP_STATUSLINE_INSTALL=1 (so postinstall does not write into your real ~/.claude), restores the embedded-PostgreSQL native symlinks that npm packing drops (V2 only), and validates the Electron binary. On Windows, the first npm run setup:v2 needs an Administrator terminal for those symlinks.
There is no ESLint/Prettier/Biome/editorconfig. tsc --noEmit is the only static gate; match surrounding style by hand.
CI (.github/workflows/quality-check.yml) runs on ubuntu/macos/windows: setup → release-notes check-range → full npm test (Linux only) or test:scripts (mac/Windows) → package:smoke:all. The full suite is not green on Windows (POSIX paths, symlinks, fake-CLI spawning) — that is why mac/Windows only run the script tests.

Read the full file on GitHub · 100 lines

Changes

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.

6d ago First seen · 100 lines · 3,373 tokens per session scan B 44990f3aa674

Subscribe to this mod's changes

AgentRecall CLAUDE.md is an instructions file published in the GitHub repository zszz3/AgentRecall (762 stars, last pushed yesterday), licensed MIT. It adds 3,373 tokens to every session, about $0.0169 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Writing and docs

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

AgentRecall CLAUDE.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade B, and why

Reads agent configuration directoriesmediumAgent snooping

How it starts

CLAUDE.md

Commands

What this file has done since we first saw it

Other instructions, from other repositories

codex AGENTS.md

vscode buildNext.instructions.md

spec-kit AGENTS.md

next.js AGENTS.md

langchain AGENTS.md

vscode oss-third-party-notices.instructions.md