Borrowing it
Nothing to install: this file belongs to panda850819/verbs. 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/panda850819/verbs/main/CLAUDE.mdgit clone --depth 1 https://github.com/panda850819/verbsWrote 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/panda850819/verbs/claude-md)<a href="https://agentmods.dev/instructions/panda850819/verbs/claude-md"><img src="https://agentmods.dev/badge/instructions/panda850819/verbs/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/panda850819/verbs/claude-md"><img src="https://agentmods.dev/badge/instructions/panda850819/verbs/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 | $0.00824 | $0.00824 |
| Opus 5.5 | $0.00330 | $0.00330 |
| Sonnet 5.5 | $0.00165 | $0.00165 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
verbs 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.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verbs (repo contract)
Verbs is an opinionated skill pack for taking software work from ambiguity to verified delivery. The user-facing README lives at the repo root. This file is the iteration contract: what an agent must keep true when changing this repo.
Layout
skills/{engineering,productivity,meta}/<name>/SKILL.md— the active skills, tiered core / ext inmanifest.toml.lib/— canonical shared modules. The copies underskills/*/lib/are GENERATED from each skill'sresources[]; never edit a vendored copy..claude-plugin/,.codex-plugin/,.agents/plugins/— GENERATED skills-only distribution metadata.maintainer/— skill-writing lore and the frontmatter spec. Not a runtime surface..out-of-scope/— rejected directions with reopen conditions. Check it before proposing any new skill, folder, or adapter.
Sync obligations (the invariants)
When adding, renaming, re-scoping, or removing a skill:
manifest.toml[skill.<name>]is the single source (tier, requires, resources, description).- Run
python3 scripts/verbs sync— it regenerates the loader JSONs (.claude-plugin/,.codex-plugin/,.agents/plugins/), the vendored lib copies, and the resource index. Hand-editing a generated file is drift the suite rejects. - Update the
RESOLVER.mdcatalog row and the skill's own description when routing changes. - Bump
[manifest] version— the bump is what refreshes installed plugin caches on both hosts. - Record the change in
CHANGELOG.md.
To retire a lib resource: remove it from resources[], run sync (it prunes
the vendored copy against the still-present canonical file), then delete the
canonical file — in that order; sync fails loud otherwise.
Verify
bash tests/run-all.sh — invocation policy, sync determinism, doctor parity,
structural lint. Green before any PR; CI runs the same suite on macOS.
Authoring bar
maintainer/writing-great-skills.md (construction lore) and
maintainer/SKILL-FRONTMATTER.md (frontmatter contract). A new skill must
name the surface it replaces or extends, clear .out-of-scope/ precedent,
and take a RESOLVER row plus a concrete routing description.
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 · 88 lines · 824 tokens per session scan A d00ae77de7c9
verbs CLAUDE.md is an instructions file published in the GitHub repository panda850819/verbs (5 stars, last pushed 1mo ago), licensed MIT. It adds 824 tokens to every session, about $0.0033 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.