agentmods.dev

claude-codeops CLAUDE.md

Project instructions for a Claude Code plugin called CodeOps, a collection of coding skills and slash commands, with a VitePress documentation site. Slash commands are named commands that start a predefined development task.

In plain words
What is it for?
It guides work across Markdown skills and commands, Bash validation scripts, Python engines, TypeScript documentation configuration, plugin files, and GitHub Pages documentation.
Why use it?
It gives the coding agent project-specific conventions, structure, tools, and validation rules for working on the plugin and its documentation.

Instructions file

4 1mo ago C scan 2,545 tokens original MIT
View the source file blendsdk/claude-codeops
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/blendsdk/claude-codeops/claude-md
Clone the repo
git clone --depth 1 https://github.com/blendsdk/claude-codeops
Per session 2,545 This file is loaded in full into every session.
When invoked 2,545 The same file — it is already loaded in full.
Security scan C 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.02545 $0.02545
Opus 5 $0.01273 $0.01273
Sonnet 5 $0.00509 $0.00509
Haiku 4.5 $0.00254 $0.00254

Measured yesterday against content hash f8ebc1eb8e5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

claude-codeops CLAUDE.md scanned grade C with 1 finding 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 yesterday.

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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- **Clean:** `rm -rf node_modules docs/.vitepress/dist docs/.vitepress/cache`
CLAUDE.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CodeOps for Claude Code

Project configuration for Claude Code. Auto-generated by /analyze_project; edit freely — re-running preserves your hand-written sections.

Overview

  • Type: Claude Code plugin (skills + commands library) with a VitePress documentation site
  • Description: The CodeOps AI-development workflow — 11 skills + 21 slash commands + always-on coding standards — packaged as an installable Claude Code plugin (the repo root is the plugin root). Ported from codeops-mcp. A user-facing docs site lives under docs/ and deploys to GitHub Pages.

Toolchain

  • Language(s): Markdown (skills/commands/standards/docs content), Bash (validation + dev installer), Python (standalone engines under scripts/), TypeScript (VitePress config only), JSON (plugin/marketplace manifests, hooks)
  • Framework(s): Claude Code plugin system; VitePress (docs site)
  • Package manager: npm (dev-only; for the docs build)
  • Test framework: Bash spec suites for the Bash engines, pytest for the standalone Python engines (dev-only, requirements-dev.txt) — Bash suites (scripts/validate.sh, scripts/docs-check.sh, scripts/migration-check.sh, scripts/compact-check.sh, scripts/roadmap-sync-check.sh, scripts/telemetry-check.sh, scripts/agents-sync-check.sh) plus the VitePress build's dead-link check

Commands

  • Build (docs): npm run docs:build
  • Dev (docs preview): npm run docs:dev → http://localhost:5173/claude-codeops/
  • Test: ./scripts/validate.sh (plugin guard), ./scripts/docs-check.sh (docs structure/CI), ./scripts/migration-check.sh (flat→nested migration engine, against scripts/fixtures/flat-repo/), ./scripts/compact-check.sh (roadmap compact engine, against scripts/fixtures/bloated-repo/), ./scripts/roadmap-sync-check.sh (roadmap sync engine, against scripts/fixtures/roadmap-repo/), ./scripts/telemetry-check.sh (telemetry utility spec suite, against scripts/fixtures/telemetry-events/, sandbox HOME), ./scripts/agents-sync-check.sh (agent-sync engine spec suite, temp repos against this plugin root), and ./scripts/pytest-check.sh (pytest suites for the standalone Python engines; skips cleanly when pytest is absent)
  • Verify (run before every commit): ./scripts/validate.sh && npm run docs:build && ./scripts/docs-check.sh && ./scripts/migration-check.sh && ./scripts/compact-check.sh && ./scripts/roadmap-sync-check.sh && ./scripts/telemetry-check.sh && ./scripts/agents-sync-check.sh && ./scripts/pytest-check.sh
  • Clean: rm -rf node_modules docs/.vitepress/dist docs/.vitepress/cache

Read the full file on GitHub · 102 lines

Changes

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.

  1. yesterday First seen · 102 lines · 2,545 tokens per session scan C f8ebc1eb8e5d

Subscribe to this mod's changes

claude-codeops CLAUDE.md is an instructions file published in the GitHub repository blendsdk/claude-codeops (4 stars, last pushed 1mo ago), licensed MIT. It adds 2,545 tokens to every session, about $0.0127 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Data and AIPlanningWriting and docsaianthropicclaudeclaude-codecodeopsdeveloper-tools
Related

Other instructions, from other repositories

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.

openai/codex · 5,182 tokens

buildNext

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).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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).

microsoft/vscode · 5,001 tokens

spec-kit 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.

github/spec-kit · 7,040 tokens

langchain 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.

langchain-ai/langchain · 4,345 tokens