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/respeak-io/episko/claude-mdgit clone --depth 1 https://github.com/respeak-io/episkoWrote 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/respeak-io/episko/claude-md)<a href="https://agentmods.dev/instructions/respeak-io/episko/claude-md"><img src="https://agentmods.dev/badge/instructions/respeak-io/episko/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 | $0.18313 | $0.18313 |
| Opus 5 | $0.09156 | $0.09156 |
| Sonnet 5 | $0.03663 | $0.03663 |
| Haiku 4.5 | $0.01831 | $0.01831 |
Grade A, and why
episko CLAUDE.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Claude runs hooks/statusLine with a stripped PATH.** Generated commands use absolute `/usr/bin/curl` and `/bin/cat`, never bare `curl`. Likewise `resolve_claude()` probes known install locations (and falls back to th How it starts
The opening of the file, as written. The whole thing — 549 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.
Episko is a Tauri v2 desktop app (Rust backend + vanilla-TS frontend) that launches and manages many coding-agent sessions at once (each in its own PTY) and streams provider capabilities such as status, context, usage and approvals back into the app. Claude Code and Codex are integrated providers; the remaining discovered CLIs use a terminal-only adapter. macOS-first; still an early spike.
The deep design notes live in docs/, one file per area, indexed at the bottom of this file. Read the matching doc before working on an area. This file keeps the commands, the module maps, and the invariants that apply to almost any change.
Commands
pnpm install # first time
pnpm tauri dev # run the app (Tauri + Vite dev server on fixed port 1420)
pnpm tauri build # production bundle
pnpm build # typechecks BOTH projects + vite build (frontend only; the beforeBuildCommand)
pnpm exec tsc --noEmit # typecheck src/ only (tsconfig is noEmit)
pnpm exec tsc -p tsconfig.test.json --noEmit # typecheck test/ (the other half)
pnpm test # vitest: frontend unit tests (test/*.test.ts)
pnpm coverage # the same suites with v8 coverage
Rust backend (run from src-tauri/): cargo check, cargo test, cargo build, cargo clippy --all-targets. Clippy is a CI gate (-- -D warnings, both OSes). Run rustup component add clippy first, then run every gate above locally before pushing, on the toolchains CI uses (stable Rust, the .nvmrc Node via nvm use). All three suites have gone red in CI for exactly one reason: the check was never run locally.
- Package manager:
pnpm, never npm (pnpm-lock.yaml;packageManagerpins the version; CI uses--frozen-lockfile). - Half the Rust is platform-
cfg-gated and invisible to any one machine. The cfg-flip trick type-checks the other half; seedocs/testing.mdfor the procedure and its limits, and commit your real changes before running it. - Never build a test's temp path by hand.
testutil::scratch_dirresolves before it returns so fixtures compare like with like;env::temp_dir()is a symlink on macOS and an 8.3 short name on the Windows runner (docs/testing.md).
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 Changed · +34 lines · +860 tokens per session 24a721c3a304
- 2d ago Changed · +66 lines · +1,822 tokens per session 22313351385a
- 6d ago First seen · 449 lines · 15,631 tokens per session scan A 136d28d43b82
episko CLAUDE.md is an instructions file published in the GitHub repository respeak-io/episko (20 stars, last pushed today), licensed MIT. It adds 18,313 tokens to every session, about $0.0916 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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.
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).
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.
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.