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/dvd90/chassis/copilot-instructionsgit clone --depth 1 https://github.com/dvd90/chassisWhat 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 | $0.00258 | $0.00258 |
| Opus 5 | $0.00129 | $0.00129 |
| Sonnet 5 | $0.00052 | $0.00052 |
| Haiku 4.5 | $0.00026 | $0.00026 |
Grade A, and why
chassis copilot-instructions.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.
What it actually says
Copilot instructions
This project follows the conventions in AGENTS.md — read it before making changes. Summary of the non-negotiables:
- Endpoints are
@route-decorated methods on aRoutablecontroller; export the class fromsrc/controllers/index.tsto mount it. There are no router files to edit. - Respond via
req.resHandler(ok,created,notFound,conflict, …), neverres.status().json(). - Signal errors by
throw new AppError(ERROR_CODES.X, message)— no try/catch in controllers; Express 5 forwards rejected promises to a central handler. - Validate input with
validate({ body: zodSchema })in the route's middleware array. - Only
src/configreadsprocess.env. - Don't edit
src/core/**to build a feature.
Scaffold a new resource with npm run gen <Name> rather than hand-writing one —
it is database-aware and wires the controller to the installed ORM.
Finish by running npm run verify (typecheck + lint + test) and make it pass
before stopping.
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 · 23 lines · 258 tokens per session scan A fe9653114c56
chassis copilot-instructions.md is an instructions file published in the GitHub repository dvd90/chassis (6 stars, last pushed 26d ago), licensed MIT. It adds 258 tokens to every session, about $0.0013 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
react-starter-kit AGENTS.md
AGENTS.md instructions for kriasoft/react-starter-kit, covering monorepo structure, tech stack, commands, database: bun db:{push,generate,migrate,studio,seed,export} and verification.
react-starter-kit CLAUDE.md
Claude Code instructions for kriasoft/react-starter-kit, a project described as: Modern React starter kit with Bun, TypeScript, Tailwind CSS, tRPC, Stripe, and Cloudflare Workers. Production-ready monorepo for building fast web apps.
react-starter-kit copilot-instructions.md
Copilot instructions for kriasoft/react-starter-kit: Read AGENTS.md in the repository root and any subdirectory AGENTS.md files for project context, conventions, and architecture details before making changes.
node-typescript-boilerplate AGENTS.md
Instructions for jsynowiec/node-typescript-boilerplate, covering agents.md, ground rules (always), typescript, node.js and testing (vitest).
nextarter-tailwind AGENTS.md
AGENTS.md instructions for agustinusnathaniel/nextarter-tailwind, covering next.js: always read docs before coding, ai agent guidance: nextarter-tailwind, 1. mental model for agents, implementation delegation and tooling strategy.
appointme CLAUDE.md
Instructions for bravodev-hub/appointme, covering claude.md, build and development commands, running the full stack (recommended), backend only and frontend only.