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/jl-cmd/claude-dev-env/copilot-instructionsgit clone --depth 1 https://github.com/jl-cmd/claude-dev-envWhat 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 | $0.00678 | $0.00678 |
| Opus 5 | $0.00339 | $0.00339 |
| Sonnet 5 | $0.00136 | $0.00136 |
| Haiku 4.5 | $0.00068 | $0.00068 |
Grade A, and why
claude-dev-env 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.
How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot instructions
Hooks in this repo enforce the conventions below. Follow them so your suggestions match what the gates accept.
Checked-in review contract: .cursor/BUGBOT.md.
Compact projection: packages/claude-dev-env/docs/CODE_RULES.md.
Naming
- Full words, no abbreviations. Never name anything
ctx,cfg,msg,btn,idx,cnt,tmp,elem, orval— writecontext,configuration,message,button,index,count,element, and so on. - Never use the vague names
result,data,output,response,value,item, ortemp. Pick a domain noun that says what the thing is. - Never start a function name with
handle_,process_,manage_, ordo_. Name the action:validate_order,send_invite,build_prompt. - Boolean names start with
is_,has_,should_,can_,was_, ordid_(camelCaseis/has/should/can/was/didin JavaScript and TypeScript). - Loop variables read as
each_<noun>. The single lettersi,j,kare fine for numeric loops andefor a caught exception.
Comments and documentation
- Write self-documenting code. Do not add new inline
#or//comments in production code — the name carries the meaning. - Docstrings on modules, classes, and functions are welcome. Keep the prose in step with the code: a docstring that lists the cases the body handles lists every one of them.
- Never drop an existing comment on a line you are not otherwise changing.
- Documentation describes the current state of the code. State what the code is and does, not how it got there.
Types
- Every function parameter and every return is typed.
- Do not use
Any, do not usecast(), and do not add a bare# type: ignore. When an ignore cannot be avoided, add a short reason after it.
Constants and configuration
- No magic values in a production function body. The numbers
0,1, and-1are fine. - Constants live in
config/or a*_constantspackage, never as a looseUPPER_SNAKEat module scope in a production file. - Search for an existing constant before adding a new one, and reuse it.
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 · 47 lines · 678 tokens per session scan A 79831627ca8b
claude-dev-env copilot-instructions.md is an instructions file published in the GitHub repository jl-cmd/claude-dev-env (6 stars, last pushed 2d ago), licensed MIT. It adds 678 tokens to every session, about $0.0034 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
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.
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).
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.