Borrowing it
Nothing to install: this file belongs to tatargabor/set-copilot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tatargabor/set-copilot/master/CLAUDE.mdgit clone --depth 1 https://github.com/tatargabor/set-copilotWrote 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/tatargabor/set-copilot/claude-md)<a href="https://agentmods.dev/instructions/tatargabor/set-copilot/claude-md"><img src="https://agentmods.dev/badge/instructions/tatargabor/set-copilot/claude-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 5.1 | $0.10909 | $0.10909 |
| Opus 5 | $0.05455 | $0.05455 |
| Sonnet 5 | $0.02182 | $0.02182 |
| Haiku 4.5 | $0.01091 | $0.01091 |
Grade A, and why
set-copilot CLAUDE.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 yesterday.
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 — 420 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Commands
npm run build # tsc → dist/ (bin + exports point at dist, so build before testing the CLI)
npm run dev -- <args> # run the CLI from TypeScript source, e.g. npm run dev -- doctor
npm test # vitest run
npx vitest run src/config.test.ts # a single file
npx vitest run -t "flushes on a sentence" # a single test by name
There is no linter. tsc runs in strict mode and is the only static check.
Tests cover the pure logic only (config resolution, keyword matching, source globbing, transcript flush rules, prompt rendering) — everything that does not need a microphone. Anything touching audio, Soniox, or the PID lifecycle is verified by running the CLI.
set-copilot doctor is the fastest way to verify a change end-to-end: it probes the real audio chain (binary → device → bytes → signal level) rather than guessing, and reports whether Soniox credentials resolve.
OpenSpec workflow
Spec-driven changes live in openspec/changes/; the applied source of truth is openspec/specs/. Drive this work through the /opsx:* skills (/opsx:propose, /opsx:apply, /opsx:archive, /opsx:continue, /opsx:status), not the raw openspec CLI by hand — the skills enforce the workflow (context-file reads, status/artifact ordering, sync-then-archive). The bare CLI is fine only for quick read-only inspection.
Commit at each step. An /opsx:apply (implementation) and an /opsx:archive (spec sync + move) are each a commit-worthy unit — commit after each rather than batching many changes into one. Doing it after the fact is fine when a run got ahead of its commits, but the default is one commit per apply and one per archive.
Two archive-time invariants, each learned from a real abort:
- Archive in dependency order. A change that
## MODIFIEDs a requirement can only archive after the change that## ADDEDit — the base spec must exist first. If an archive fails with "target spec does not exist", archive the originating change first. - A MODIFIED requirement must carry forward every base scenario. The archiver refuses to silently drop a scenario. If a scenario is genuinely obsolete, don't just delete it — reframe it to its surviving intent or move it under a
## REMOVEDrequirement. And a delta that removes every requirement from a spec leaves it empty (invalid): retire the capability with a single tombstone## ADDEDrequirement that redirects to its successor, so the audit trail and the removal reasons survive.
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.
- yesterday First seen · 420 lines · 10,909 tokens per session scan A 3627eac8ff89
set-copilot CLAUDE.md is an instructions file published in the GitHub repository tatargabor/set-copilot (2 stars, last pushed 14d ago), licensed MIT. It adds 10,909 tokens to every session, about $0.0545 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 2026-09-04.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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).
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.
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.