Borrowing it
Nothing to install: this file belongs to juliakrivchikova/AccordAgents-desktop-app. 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/juliakrivchikova/AccordAgents-desktop-app/main/CLAUDE.mdgit clone --depth 1 https://github.com/juliakrivchikova/AccordAgents-desktop-appWrote 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/juliakrivchikova/accordagents-desktop-app/claude-md)<a href="https://agentmods.dev/instructions/juliakrivchikova/accordagents-desktop-app/claude-md"><img src="https://agentmods.dev/badge/instructions/juliakrivchikova/accordagents-desktop-app/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/juliakrivchikova/accordagents-desktop-app/claude-md"><img src="https://agentmods.dev/badge/instructions/juliakrivchikova/accordagents-desktop-app/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.02958 | $0.02958 |
| Opus 5 | $0.01479 | $0.01479 |
| Sonnet 5 | $0.00592 | $0.00592 |
| Haiku 4.5 | $0.00296 | $0.00296 |
Grade C, and why
AccordAgents-desktop-app CLAUDE.md scanned grade C with 2 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 12d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- `cliAgents.ts` — Runs `codex`, `claude`, and `agy` (Antigravity/Gemini) CLIs. Detects them via `which`, then spawns `codex exec` / `claude` with carefully constructed argv: `--sandbox read-only`, `--cd <repo>`, `--skip Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
- `cliAgents.ts` — Runs `codex`, `claude`, and `agy` (Antigravity/Gemini) CLIs. Detects them via `which`, then spawns `codex exec` / `claude` with carefully constructed argv: `--sandbox read-only`, `--cd <repo>`, `--skip How it starts
The opening of the file, as written. The whole thing — 99 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.
NON-NEGOTIABLE PRODUCT INVARIANT: DEDICATED CLI PARITY
WORKING WITH ONE SPECIFIC PARTICIPANT IN ACCORDAGENTS CHAT MUST FEEL LIKE WORKING WITH THAT AGENT THROUGH ITS REGULAR, DEDICATED CLI.
Before every product, architecture, implementation, UI, and commit decision, explicitly check that this invariant still holds. AccordAgents must mirror the current CLI behavior at the time a feature is implemented, including output rendering and streaming, permissions and approvals, sandboxing, model selection, sessions and resume behavior, compaction, goals, skills and rules, MCPs and tools, cancellation, errors, warnings, and user controls. The user should not need to learn different single-agent behavior merely because the agent is running inside AccordAgents.
Treat the dedicated CLI as the source of truth. Do not invent app-specific semantics for a single participant when the CLI already defines them. If multi-participant coordination inherently requires a difference, keep the divergence as narrow as possible, make it visible to the user, document why it exists, and add verification for both the parity path and the divergence. CLI behavior can evolve; verify the current behavior when implementing or revisiting a feature rather than relying on an old assumption. Any unexplained mismatch is a product correctness bug.
Commands
Prefer the Makefile aliases; they wrap the npm scripts in package.json.
make dev— Vite dev server + Electron with live reload. Internally runsnpm run build:mainfirst because Electron loads the compiled main/preload fromdist/maineven in dev.make build— Compile main process (tsc -p tsconfig.main.json) thenvite buildthe renderer.make start— Build, then run Electron fromdist.make typecheck— Strict TS checks for both main and renderer projects (tsc --noEmitagainst each tsconfig).make clean— Removedist.npm run test:accord— Build the main process, then run focused Accord launcher preference and target reconciliation tests.npm run test:permissions— Build the main process, then run targeted Node service tests for chat permissions/cancellation, repo file mentions, chat rename, role archive behavior, participant request threads, git repo-file listing, CLI permission handling, and warnings.npm run test:app-skills— Build the main process, then run app-skill service tests.
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.
- 12d ago First seen · 99 lines · 2,958 tokens per session scan C cba27d140d87
AccordAgents-desktop-app CLAUDE.md is an instructions file published in the GitHub repository juliakrivchikova/AccordAgents-desktop-app (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 2,958 tokens to every session, about $0.0148 per session on Opus 5. A static security scan graded it C with 2 findings (reads agent configuration directories, reads mcp configuration). 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.
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).
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).