Borrowing it
Nothing to install: this file belongs to qhkm/zeptoclaw. 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/qhkm/zeptoclaw/main/CLAUDE.mdgit clone --depth 1 https://github.com/qhkm/zeptoclawWrote 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/qhkm/zeptoclaw/claude-md)<a href="https://agentmods.dev/instructions/qhkm/zeptoclaw/claude-md"><img src="https://agentmods.dev/badge/instructions/qhkm/zeptoclaw/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/qhkm/zeptoclaw/claude-md"><img src="https://agentmods.dev/badge/instructions/qhkm/zeptoclaw/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 | $0.02190 | $0.02190 |
| Opus 5 | $0.01095 | $0.01095 |
| Sonnet 5 | $0.00438 | $0.00438 |
| Haiku 4.5 | $0.00219 | $0.00219 |
Grade A, and why
zeptoclaw 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ZeptoClaw
Fast, small, secure, local-first personal AI assistant infrastructure. Fresh configs default to assistant mode with dangerous tool approvals enabled.
Quick Reference
cargo build --release # Build
cargo nextest run --lib # Test (use nextest to avoid OOM)
cargo clippy -- -D warnings && cargo fmt # Lint & format
./target/release/zeptoclaw agent -m "Hello" # Run agent
./target/release/zeptoclaw config check # Validate config
./target/release/zeptoclaw provider status # Check providers
For full CLI reference, slash commands, and gateway commands see docs/claude/commands.md.
Agent Workflow — Task Tracking Protocol
Every Claude Code session MUST follow these rules:
1. Session Start — Check open issues
gh issue list --state open --limit 20
Present issues, ask what to work on.
2. New Work — Create issue first
gh issue create \
--title "feat: short description" \
--label "feat,area:tools" \
--body "Brief description of the work."
Labels: bug, feat, rfc, chore, docs + area:tools, area:channels, area:providers, area:safety, area:config, area:cli, area:memory + P1-critical, P2-high, P3-normal. Skip for trivial changes.
3. Session End — Link and close
- Follow the PR guidelines in
docs/claude/pr.mdand use the template at.github/PULL_REQUEST_TEMPLATE.md - PR body: include
Closes #N - NEVER merge PRs without explicit user approval. Wait for CI, present URL, merge only after user says to
- Merge:
gh pr merge <number> --squash --delete-branch --admin - Direct commit:
gh issue close N --comment "Done in <commit-sha>" - Update
CLAUDE.mdandAGENTS.mdper the post-implementation checklist
Pre-Push Checklist (MANDATORY)
cargo fmt && cargo clippy -- -D warnings && cargo nextest run --lib && cargo test --doc && cargo fmt -- --check
After subagent work: ALWAYS run cargo fmt before committing.
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 · +4 tokens per session 927ea6074bf8
- 3d ago Changed · +2 lines · +114 tokens per session a39c6e74b290
- 9d ago First seen · 135 lines · 2,072 tokens per session scan A 0de95ff3370f
zeptoclaw CLAUDE.md is an instructions file published in the GitHub repository qhkm/zeptoclaw (650 stars, last pushed today), licensed Apache-2.0. It adds 2,190 tokens to every session, about $0.0110 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).
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.
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.