Borrowing it
Nothing to install: this file belongs to jianzhichun/emerge. 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/jianzhichun/emerge/main/CLAUDE.mdgit clone --depth 1 https://github.com/jianzhichun/emergeWrote 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/jianzhichun/emerge/claude-md)<a href="https://agentmods.dev/instructions/jianzhichun/emerge/claude-md"><img src="https://agentmods.dev/badge/instructions/jianzhichun/emerge/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/jianzhichun/emerge/claude-md"><img src="https://agentmods.dev/badge/instructions/jianzhichun/emerge/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 | $0.04879 | $0.04879 |
| Opus 5 | $0.02440 | $0.02440 |
| Sonnet 5 | $0.00976 | $0.00976 |
| Haiku 4.5 | $0.00488 | $0.00488 |
Grade A, and why
emerge 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
You — reading this — are building this plugin. You are not its user.
The user is another Claude session, tomorrow, running Claude Code with this plugin installed. It will never read this file. It will only feel what you leave behind: which intents auto-promote, which failures survive into the next reflection, which pipelines compose, which hooks open doors vs bar them.
Every commit here is a contract with a Claude you will never meet. Your job is to expand its action surface, not polish the plumbing. When in doubt, ship the change that lets the next Claude skip a step, remember a failure, or compose a capability — even if the diff is larger or uglier than a "clean" refactor.
North Star — three capability axes for operator-Claude
- Skip inference on solved work. The flywheel's payoff is zero-LLM execution of stable intents. Manual gates,
_pending/pipelines, confirmation prompts, "just to be safe" dialogs — these tax every future session on work that was already learned. Auto-promote, don't gate. Humans veto by rolling back, not by approving forward. - Failed once → learn forever. When an intent demotes, the root cause must reach the next session through reflection injection (
SpanTracker.format_reflection→SessionStart/UserPromptSubmit/PreCompact). A signal that dies insidetransition_historyand never surfaces in reflection is a bug, no matter how well the cockpit shows it. "Failed" includes silent wrongness — a crystallized bridge that returnsNone/[]/ malformed data without raising still violates its contract. When adding bridge-path code, default to treating "returned nothing useful" as a failure unless the intent is provably allowed to be empty. - Compose, don't re-derive.
connector.mode.nameintents are building blocks. Stable pipelines should compose (new = stable_A >> stable_Binherits both parents' stable status + verify history) so learning cost stays sub-linear in intent count.
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.
- 10d ago First seen · 141 lines · 4,879 tokens per session scan A 5ead4d0148c7
emerge CLAUDE.md is an instructions file published in the GitHub repository jianzhichun/emerge (107 stars, last pushed 4mo ago), licensed MIT. It adds 4,879 tokens to every session, about $0.0244 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.
Other instructions, from other repositories
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).
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.
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).
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.