agentmods.dev

jc CLAUDE.md

jc CLAUDE.md is an instructions file for coding agents from jeapostrophe/jc. It costs 612 tokens per session, scanned A, original, MIT.

Project-specific instructions for jc, a Claude Code orchestrator that runs development tasks in one window. They describe required checks, files to edit, and testing rules for that Rust project.

In plain words
What is it for?
Working on the jc repository, especially before committing Rust changes. They guide plan triage, workspace tests, formatting and lint checks, and safe updates to the vendored gpui-component source.
Why use it?
They give a coding agent the repository’s local rules before it changes code. This reduces missed formatting, lint, test, and vendored-source requirements.

Instructions file

not rated 45 +1 6d ago A scan 612 tokens original MIT
View the source file jeapostrophe/jc
Install

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.

agentmods
npx agentmods add instructions/jeapostrophe/jc/claude-md
Clone the repo
git clone --depth 1 https://github.com/jeapostrophe/jc

Wrote 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.

agentmods badge for jc CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jeapostrophe/jc/claude-md.svg)](https://agentmods.dev/instructions/jeapostrophe/jc/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jeapostrophe/jc/claude-md"><img src="https://agentmods.dev/badge/instructions/jeapostrophe/jc/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 612 This file is loaded in full into every session.
When invoked 612 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00612 $0.00612
Opus 5 $0.00306 $0.00306
Sonnet 5 $0.00122 $0.00122
Haiku 4.5 $0.00061 $0.00061

Measured 4d ago against content hash fdc050c49b72, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

jc 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 4d 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.

CLAUDE.md · 16 lines

What it actually says

  • Don't read the TODO.md file.
  • Before committing, run cargo fmt --all -- --check && cargo clippy --workspace -- -D warnings to catch CI failures locally.
  • If you see any [?] labels in PLAN.md, triage them first: read the task, examine the relevant code, and replace [?] with the correct difficulty label ([T]/[E]/[H]/[D]) before starting other work.
  • Run cargo test --workspace after any code changes. Keep existing tests passing and add new tests for any new or changed behavior.
  • vendor/gpui-component is the source of truth for local changes and is committed to git. vendor/patches/ does NOT reproduce it — the patches are written against 4-space upstream while the tree is formatted to this repo's 2-space rustfmt, and some local changes (the tree-sitter read-callback and InputEdit crash fix in highlighter.rs / input/mode.rs) have no patch file at all. Edit the vendored tree directly and commit.
  • scripts/update-gpui-component.sh re-vendors from the cargo cache and is LOSSY: it deletes the tree and re-applies only vendor/patches/, silently reverting local changes. It refuses to run over uncommitted changes. Only run it to pick up a new upstream version, and afterwards recover local changes from git (git diff <pre-vendor-rev> -- vendor/gpui-component) and re-apply them by hand.
  • When a picker confirm handler calls a method that sets focus itself (e.g. switch_to_session), drop pre_picker_focus instead of restoring it — the stale handle points at a view that may no longer be in a pane, causing focus to be lost.
  • gpui performance rules:
    • Never use window.refresh() — use cx.notify() on the specific entity.
    • Only call cx.notify() when state actually changed. Guard with a comparison or use the return value of mutations (e.g. HashSet::insert() returns false if already present).
    • Never call cx.notify() inside cx.observe() callbacks unless unavoidable — it cascades re-renders.
    • Always store Subscription return values from cx.observe() / cx.subscribe() in a struct field. A dropped Subscription leaks observer callbacks.
    • Use uniform_list for rendering collections that can exceed ~50 items. Never .children() an unbounded Vec.
    • Minimize nested background layers — gpui has 5-6x pixel overdraw from alpha-blended rounded rects.
    • Never do blocking I/O (git, filesystem, subprocess) on the main thread or in async tasks on the main executor. Use cx.background_executor().spawn() or std::thread::spawn.
Changes

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.

  1. 4d ago First seen · 16 lines · 612 tokens per session scan A fdc050c49b72

Subscribe to this mod's changes

jc CLAUDE.md is an instructions file published in the GitHub repository jeapostrophe/jc (45 stars, last pushed 6d ago), licensed MIT. It adds 612 tokens to every session, about $0.0031 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 2026-08-30.

claude-codemacos
Related

Other instructions, from other repositories

FluidAudio copilot-instructions.md

Copilot instructions for FluidInference/FluidAudio, covering fluidaudio - agent development guide, build & test commands, architecture, critical rules and code style (swift-format config).

FluidInference/FluidAudio · 552 tokens

speech-swift AGENTS.md

AGENTS.md instructions for soniqo/speech-swift, covering agent instructions, communication style, workflow, running tests and benchmarks — sequential and memory-aware and git conventions.

soniqo/speech-swift · 5,053 tokens

codex-provider-sync AGENTS.md

Instructions for Dailin521/codex-provider-sync, covering ai / agent operator guide, vnext architecture baseline, goal, choose the interface and safe operating flow.

Dailin521/codex-provider-sync · 1,480 tokens

liney AGENTS.md

AGENTS.md instructions for everettjf/liney, covering liney repository collaboration guide, 交流语言 / communication language, project overview, repository layout and build and test.

everettjf/liney · 1,589 tokens

Starcat AGENTS.md

AGENTS.md instructions for starcat-app/Starcat, covering agents.md, 🚨 硬性铁律（每次写代码前必读，违反即返工）, 🌿 git 分支与 worktree（强制）, 🧭 主进度索引（每次开工前必读） and 状态符号（与功能实现总览.md 同步）.

starcat-app/Starcat · 7,439 tokens

skills-manager CLAUDE.md

Instructions for yibie/skills-manager, covering skills manager - development guide, tui engine: blessed, 核心原则, 参考文档 and 正确的 list 用法.

yibie/skills-manager · 642 tokens