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/ssssota/chapplin/agents-mdgit clone --depth 1 https://github.com/ssssota/chapplinWhat 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 | $0.00803 | $0.00803 |
| Opus 5 | $0.00402 | $0.00402 |
| Sonnet 5 | $0.00161 | $0.00161 |
| Haiku 4.5 | $0.00080 | $0.00080 |
Grade A, and why
chapplin 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 3d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Goal
- Provide stable, safe operating rules for LLM agents working in this repository.
- Prioritize minimal, correct diffs that match existing patterns.
Project Summary
chapplinis a framework for building MCP servers with MCP Apps from a single TypeScript codebase.- Primary users are developers who define MCP tools/resources/prompts and optionally attach UI apps to tools.
- The monorepo includes the runtime framework (
packages/chapplin), scaffolding CLI (packages/create-chapplin), examples, e2e fixtures, and docs website. - Core workflow: define server features (
defineTool,defineResource,definePrompt) and, when needed, define tool UIs withdefineApp. - Vite integration in
packages/chapplin/src/vitehandles file collection, virtual modules, dev server behavior, and app build wiring. - Non-goals for most tasks: redesigning public APIs without request, broad refactors across packages, or changing templates/e2e fixtures unrelated to the requested scope.
Session Bootstrap
- Read in order:
README.md->packages/chapplin/README.md->packages/chapplin/src/vite/readme.md-> target package README. - Before making edits, write a 3-line summary: project goal, target area, expected validation commands.
- If requirements are ambiguous, ask before implementing.
Repo Map
packages/chapplin: core framework package (defineTool,defineApp, vite plugin, CLI entry).packages/chapplin/src/vite: vite integration and plugin pipeline.packages/chapplin/dev-ui: dev UI used by the framework during development.packages/create-chapplin: project scaffolding tool and templates.examples/*: runnable sample apps.e2e: Playwright end-to-end tests and fixture projects.website: docs site..github/workflows: CI rules to mirror locally.
Working Rules
- Follow existing code style and file layout before introducing new patterns.
- Keep changes scoped to the requested task; avoid opportunistic refactors.
- Do not edit generated or dependency artifacts directly:
node_modules,dist,website/.astro,e2e/test-results. - Avoid destructive git/file commands unless explicitly requested.
- Prefer targeted checks for touched packages first, then broader checks if needed.
- When changing behavior, add or update tests in the nearest relevant package.
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.
- 3d ago First seen · 61 lines · 803 tokens per session scan A 59ed6135537a
chapplin AGENTS.md is an instructions file published in the GitHub repository ssssota/chapplin (16 stars, last pushed 6d ago), licensed MIT. It adds 803 tokens to every session, about $0.0040 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
webweaver-mcp-server CLAUDE.md
Claude Code instructions for webweaver-nexus/webweaver-mcp-server, covering claude.md, project overview, architecture, server: one core, two entry points and client app lifecycle.
splatter-mcp-app AGENTS.md
AGENTS.md instructions for kstonekuan/splatter-mcp-app, a project described as: MCP app for generating and viewing 3D models using 3D Gaussian Splatting.
splatter-mcp-app CLAUDE.md
Claude Code instructions for kstonekuan/splatter-mcp-app, a project described as: MCP app for generating and viewing 3D models using 3D Gaussian Splatting.
ebay-mcp AGENTS.md
Instructions for YosefHayim/ebay-mcp, covering agents.md, what this is, instruction sources, validation commands and module map (src/).
mcp-odoo CLAUDE.md
Claude Code instructions for erpipe-org/mcp-odoo: Guidance for Claude Code (claude.ai/code) working in this repository.
ebay-mcp copilot-instructions.md
Instructions for YosefHayim/ebay-mcp, covering github copilot instructions, core expectations, schema and api patterns, documentation and tests and validation.