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/zszz3/agentrecall/agents-mdgit clone --depth 1 https://github.com/zszz3/AgentRecallWrote 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/zszz3/agentrecall/agents-md)<a href="https://agentmods.dev/instructions/zszz3/agentrecall/agents-md"><img src="https://agentmods.dev/badge/instructions/zszz3/agentrecall/agents-md.svg" alt="Measured on agentmods" 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 | $0.02963 | $0.02963 |
| Opus 5 | $0.01482 | $0.01482 |
| Sonnet 5 | $0.00593 | $0.00593 |
| Haiku 4.5 | $0.00296 | $0.00296 |
Grade A, and why
AgentRecall 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 4d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository instructions
AgentRecall is a local Electron application that indexes, displays, and resumes coding-agent sessions. The repository ships two applications from one npm workspace: V1 is the stable product and V2 is the preview product with the upgraded session experience, PostgreSQL storage, Runtime, Agents, Chat, Workflow, Eval, MCP, Memory, and a managed Skill library. Read README.md for the product surface and CONTRIBUTING.md for the contributor workflow.
Repository map
apps/main-1.0/ Stable Electron app; SQLite and mostly synchronous stores
apps/main-2.0/ Preview Electron app; PostgreSQL and asynchronous stores
src/main/ Electron main process, services, IPC handlers, OS integration
src/preload/ Narrow typed bridge exposed to renderer windows
src/renderer/ React UI; browser-safe code only
src/core/ Domain logic, loaders, persistence, and shared application types
src/automation/ V2 Agent, Chat, Workflow, Eval, and runtime engine
scripts/ Repository setup, release-note, packaging, and release checks
docs/ User guides, troubleshooting, and durable design documents
.release-notes/ User-facing release-note fragments consumed by the release workflow
assets/ Repository-level images and distributable assets
Keep changes in the lowest owning area. Do not place V2-only behavior in shared V1 code, renderer presentation in persistence modules, or OS/filesystem operations in React components.
Commands
npm run setup:v1 # install the V1 workspace
npm run setup:v2 # install the V2 workspace
npm run dev:v1 # run V1 from source
npm run dev:v2 # run V2 from source
npm run test:v1 # V1 tests
npm run test:v2 # V2 tests
npm run typecheck # typecheck both apps
npm run build # build both apps
npm run release-note:check # validate release-note routing and format
npm run package:smoke # isolated V1 package smoke test
npm run package:smoke:v2 # isolated V2 package smoke test
npm run release:preflight # full release preflight; expensive
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.
- 4d ago First seen · 128 lines · 2,963 tokens per session scan A d7637238f1a3
AgentRecall AGENTS.md is an instructions file published in the GitHub repository zszz3/AgentRecall (778 stars, last pushed 4d ago), licensed MIT. It adds 2,963 tokens to every session, about $0.0148 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.