Borrowing it
Nothing to install: this file belongs to bunhine0452/Ocul-PM. 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/bunhine0452/Ocul-PM/main/CLAUDE.mdgit clone --depth 1 https://github.com/bunhine0452/Ocul-PMWrote 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/bunhine0452/ocul-pm/claude-md)<a href="https://agentmods.dev/instructions/bunhine0452/ocul-pm/claude-md"><img src="https://agentmods.dev/badge/instructions/bunhine0452/ocul-pm/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/bunhine0452/ocul-pm/claude-md"><img src="https://agentmods.dev/badge/instructions/bunhine0452/ocul-pm/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 | $0.03362 | $0.03362 |
| Opus 5.5 | $0.01345 | $0.01345 |
| Sonnet 5.5 | $0.00672 | $0.00672 |
| Haiku 4.5 | $0.00336 | $0.00336 |
Grade A, and why
Ocul-PM 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 today.
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 — 91 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.
What this is
Ocul-PM (ocul-pm) is a Tauri 2 native desktop app (Rust backend + system webview, not Electron) — a local-first AI project manager that records what external coding agents (Claude Code, Cursor, Gemini CLI) do, as human-readable markdown work-journals. All data stays in each project's .oculpm/ directory plus a local SQLite cache; the only things that leave the machine are ones the user starts — LLM API calls, update checks, GitHub fetches (release notes, plugin/skill bundles), a one-time embedding-model download, Claude Code/Codex inside the app (their provider traffic plus a lockfile-pinned ACP adapter install from npm — once per pinned version) — plus whatever the user's own tools do once the app runs them for the user (terminal commands, the new-project wizard's scaffold CLIs — pnpm create vite / npx create-next-app@latest fetch from npm — language servers in a trusted project). src-tauri/tests/egress_inventory.rs is the ledger that keeps this list honest — it fails the build on a new outbound call that is neither guarded nor listed with a reason — and egress_spawn_ledger.rs beside it does the same for child processes: every launch site is classified network-capable (with what opens that door) or local.
UI language is Korean — match it in UI strings, journals, and commit messages.
Scope freeze (since 2026-10-08)
The periphery (code editor · LSP · DAP · terminal/PTY host · ACP chat · mobile bridge · Notion · themes · code graph) is now as large as the core (journal · planner · Today), and of the 211 fix commits in the 60 days to 2026-10-08, 95 touched the periphery against 80 for the core. One maintainer cannot keep both honest — an external review said so, and the numbers agree.
- Don't build a new screen, a new external integration, or a new long-lived process or network listener. Proposing one is fine; building it needs the user's explicit go-ahead and a named existing surface it retires.
- Do fix, shrink, or replace what exists. A replacement ends by removing the old path, not by keeping both (cf.
native-agent-drivers{#drop-node}). - Removal candidates and the numbers behind them: plan
external-review-2026-10-08. - Already removed (2026-10-24): the mobile bridge (Tailscale phone web app), the DAP debugger, the Code Map screen, the remote theme gallery (GitHub/oculpm.com theme downloads) and the VS Code extension; Notion went 2026-10-14. Leftover unused DB tables stay —
mobile_devices(migration 029),graph_nodes·graph_edges·symbol_relations— don't reuse those names.
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.
- today Changed · +1 lines · +91 tokens per session 46a2d12a64c8
- 11d ago Changed · -21 tokens per session 1273643cd651
- 14d ago Changed · +95 tokens per session b84ba5d6bcd4
- 16d ago Changed · +8 lines · +230 tokens per session f0d260a9e134
- 18d ago Changed · +27 tokens per session c218ecbdb193
- 1mo ago Changed · +64 tokens per session 8f23df5f9ff1
- 1mo ago Changed · +603 tokens per session 37a664851a8d
- 1mo ago First seen · 82 lines · 2,273 tokens per session scan A e60f4381c31f
Ocul-PM CLAUDE.md is an instructions file published in the GitHub repository bunhine0452/Ocul-PM (7 stars, last pushed today), licensed MIT. It adds 3,362 tokens to every session, about $0.0134 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 2026-08-31.
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.