Borrowing it
Nothing to install: this file belongs to jeapostrophe/jc. 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/jeapostrophe/jc/master/CLAUDE.mdgit clone --depth 1 https://github.com/jeapostrophe/jcWrote 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/jeapostrophe/jc/claude-md)<a href="https://agentmods.dev/instructions/jeapostrophe/jc/claude-md"><img src="https://agentmods.dev/badge/instructions/jeapostrophe/jc/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/jeapostrophe/jc/claude-md"><img src="https://agentmods.dev/badge/instructions/jeapostrophe/jc/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 | $0.00612 | $0.00612 |
| Opus 5.5 | $0.00245 | $0.00245 |
| Sonnet 5.5 | $0.00122 | $0.00122 |
| Haiku 4.5 | $0.00061 | $0.00061 |
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 1mo 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.
What it actually says
- Don't read the TODO.md file.
- Before committing, run
cargo fmt --all -- --check && cargo clippy --workspace -- -D warningsto 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 --workspaceafter any code changes. Keep existing tests passing and add new tests for any new or changed behavior. vendor/gpui-componentis 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 andInputEditcrash fix inhighlighter.rs/input/mode.rs) have no patch file at all. Edit the vendored tree directly and commit.scripts/update-gpui-component.shre-vendors from the cargo cache and is LOSSY: it deletes the tree and re-applies onlyvendor/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), droppre_picker_focusinstead 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()— usecx.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()returnsfalseif already present). - Never call
cx.notify()insidecx.observe()callbacks unless unavoidable — it cascades re-renders. - Always store
Subscriptionreturn values fromcx.observe()/cx.subscribe()in a struct field. A droppedSubscriptionleaks observer callbacks. - Use
uniform_listfor rendering collections that can exceed ~50 items. Never.children()an unboundedVec. - 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()orstd::thread::spawn.
- Never use
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.
- 1mo ago First seen · 16 lines · 612 tokens per session scan A fdc050c49b72
jc CLAUDE.md is an instructions file published in the GitHub repository jeapostrophe/jc (45 stars, last pushed yesterday), licensed MIT. It adds 612 tokens to every session, about $0.0024 per session on Opus 5.5. 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.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.