Borrowing it
Nothing to install: this file belongs to htlin222/hahow-mentor-agent. 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/htlin222/hahow-mentor-agent/main/CLAUDE.mdgit clone --depth 1 https://github.com/htlin222/hahow-mentor-agentWrote 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/htlin222/hahow-mentor-agent/claude-md)<a href="https://agentmods.dev/instructions/htlin222/hahow-mentor-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/htlin222/hahow-mentor-agent/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/htlin222/hahow-mentor-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/htlin222/hahow-mentor-agent/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 | $0.00987 | $0.00987 |
| Opus 5 | $0.00494 | $0.00494 |
| Sonnet 5 | $0.00197 | $0.00197 |
| Haiku 4.5 | $0.00099 | $0.00099 |
Grade A, and why
hahow-mentor-agent 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 9d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hahow Mentor Agent — project notes for Claude
Python CLI for triaging Hahow course discussions and homework. Mentor identity
comes from .env (ID / PASSWORD). Drafter persona and locale strings come
from config.toml (gitignored; falls back to config.example.toml). All
commands run with uv.
Personal workflow notes, environment-specific gotchas, and "do not repeat these mistakes" lore live in
CLAUDE.local.md(gitignored). Read that file first if it exists in your working tree.
Auto-relay: hahow-watcher channel (research preview)
For a long-running session that should react to new questions automatically:
make start-with-channels
# → claude --dangerously-load-development-channels server:hahow-watcher \
# --dangerously-skip-permissions
channels/hahow-watcher/hahow-watcher.ts is an MCP channel server (Bun +
@modelcontextprotocol/sdk) that:
- Runs
make refresheveryHAHOW_POLL_MINUTES(default 60). - Diffs
build/unread.jsonagainst~/.hahow-mentor/drafts/andposted.log. - For each tick that finds new ids, emits
notifications/claude/channelwith metacount=<N> courses=<title=N,title=N>and a summary body listing up to 10 ids + course + title + image-attachment count. - Channel is one-way. Replies happen via the regular
make post-allflow after the mentor audits drafts.
When Claude sees a <channel source="hahow-watcher" count="N" ...> tag,
invoke the batch-draft-hahow skill. Drafts only — never call
make post-all automatically.
Smoke-test the poll loop without Claude: make poll-channel-once.
Routine: batch-draft outstanding student questions
On phrases like "batch draft", "draft 全部還沒回的", "處理一輪 Q&A",
invoke the local skill batch-draft-hahow (in .claude/skills/). It encodes
the full workflow. Short version:
make refresh— snapshots unread+unresolved intobuild/unread.jsonand downloads every attached image to~/.hahow-mentor/audits/discussion-<id>/.- For each question with attached images, use the Read tool on the
downloaded PNG(s) directly, then write a one-sentence description per id
into
build/image_notes.json. - For technical questions, batch WebSearch in parallel (≤5 per message).
Paste a short summary per id into
build/web_findings.json. Skip WebSearch for trivial / meta questions. make draft— runs codex against every question that does not already have a draft. Output →~/.hahow-mentor/drafts/<id>.md.make status— prints which questions have drafts, ages, posted-flag.- Report a table to the mentor. Never post automatically.
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.
- 9d ago First seen · 85 lines · 987 tokens per session scan A 4597b2bb0bfc
hahow-mentor-agent CLAUDE.md is an instructions file published in the GitHub repository htlin222/hahow-mentor-agent (1 stars, last pushed 3mo ago), licensed MIT. It adds 987 tokens to every session, about $0.0049 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 2026-08-31.
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.