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/massimoalbarello/context-use-old/agents-mdgit clone --depth 1 https://github.com/massimoalbarello/context-use-oldWhat 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 | $0.00823 | $0.00823 |
| Opus 5 | $0.00411 | $0.00411 |
| Sonnet 5 | $0.00165 | $0.00165 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
context-use-old 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 2d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Use contributor guide
Context Use is a Bun and TypeScript monorepo for a self-hosted knowledge base. The same release contains several independently deployed backend processes, a React dashboard, a deployment CLI, database tooling, and Nango integrations.
Read the nearest nested AGENTS.md before changing a workspace. More specific guidance overrides
this file.
Repository map
apps/server— private application, anonymous public application, and storage broker processes.apps/web— authenticated React dashboard.apps/cli— installation and operational CLI.packages/database— PostgreSQL schema, repositories, administrative commands, and test support.packages/shared— temporary shared contracts; this will be decomposed as API contracts become explicit.packages/openclaw-context-use— published OpenClaw memory integration.nango-integrations— separately built Nango sync contracts.infraanddeploy— infrastructure and runtime topology.
Non-negotiable boundaries
- Preserve the three backend trust domains. The private application owns dashboard, auth, MCP, and confirmation in process; the public application owns anonymous publication; only the storage broker receives AWS, S3, and KMS authority. Each process receives only its own database role, secrets, networks, and storage capability.
- HTTP controllers call services; services call repositories. Do not skip a layer.
- SQL and external-system mechanics belong in repositories. Business policy does not.
- Construct dependencies in an application composition root. Importing a module must not open a pool, start a server, read unrelated secrets, or mutate global state.
- Derive types from the schema or client that owns them. Do not maintain a second handwritten copy.
- Share business logic across API surfaces, not authentication or exposure policy. Dashboard and MCP controllers may call the same service while retaining distinct guards and response models.
- Keep refactoring changes behavior-preserving unless the PR explicitly names a behavior change.
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.
- 2d ago First seen · 78 lines · 823 tokens per session scan A 9bcd1594815c
context-use-old AGENTS.md is an instructions file published in the GitHub repository massimoalbarello/context-use-old (2 stars, last pushed 6d ago), licensed MIT. It adds 823 tokens to every session, about $0.0041 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
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.