agentmods.dev

devpowers CLAUDE.md

A set of instructions for building and maintaining a Claude Code plugin. Claude Code is a coding assistant that can load project-specific extensions such as skills, commands, agents, and hooks.

In plain words
What is it for?
It helps organize plugin manifests and component folders, write portable skill references, and follow repository-specific setup guidance. It is documentation rather than a standalone feature.
Why use it?
It gives contributors shared rules for the plugin's file layout, references, authentication, and development conventions.

Instructions file

2 23d ago A scan 826 tokens original MIT
View the source file kolodkin/devpowers
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/kolodkin/devpowers/claude-md
Clone the repo
git clone --depth 1 https://github.com/kolodkin/devpowers
Per session 826 This file is loaded in full into every session.
When invoked 826 The same file — it is already loaded in full.
Security scan A 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 $0.00826 $0.00826
Opus 5 $0.00413 $0.00413
Sonnet 5 $0.00165 $0.00165
Haiku 4.5 $0.00083 $0.00083

Measured yesterday against content hash 7db00011e1b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devpowers CLAUDE.md scanned grade A 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Skills that talk to GitHub (`check-pr`, `action-run`, `action-check`) authenticate through the `github` MCP server, registered via `/setup-mcp github`. It uses a single long-lived `GH_TOKEN` Personal Access Token — the
CLAUDE.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This repository is a Claude Code plugin that is also its own single-plugin marketplace. The repo root is the plugin root: .claude-plugin/plugin.json is the plugin manifest, and .claude-plugin/marketplace.json catalogs it with "source": "./". Component directories (skills/, commands/, agents/, hooks/) live at the repo root.

Layout

.claude-plugin/
  marketplace.json              # marketplace catalog (source: "./")
  plugin.json                   # plugin manifest
skills/<skill-name>/
  SKILL.md                      # skill entry point
  ...                           # optional scripts, references

Conventions

  • Reference bundled scripts from SKILL.md using plain relative paths (e.g. scripts/download.sh, scripts/update.sh). Claude resolves them against the skill's install directory, so the same SKILL.md works for both plugin installs (under ~/.claude/plugins/cache/.../skills/<name>/) and project-level installs (under <project>/.claude/skills/<name>/). Avoid ${CLAUDE_PLUGIN_ROOT} inside skill bodies — it's empty when the skill is installed project-level, and ${CLAUDE_PROJECT_DIR} isn't reliably set in Bash tool invocations either (anthropics/claude-code#6023). Reserve ${CLAUDE_PLUGIN_ROOT} for hooks/*.json and MCP/LSP configs, where the harness guarantees it's set.
  • Use ${CLAUDE_PLUGIN_DATA} for state that must survive plugin updates.
  • All component directories (skills/, commands/, agents/, hooks/) live at the plugin root — never inside .claude-plugin/.

GitHub auth

  • Skills that talk to GitHub (check-pr, action-run, action-check) authenticate through the github MCP server, registered via /setup-mcp github. It uses a single long-lived GH_TOKEN Personal Access Token — the same token also covers the one remaining REST curl escape hatch — the in-progress CI/run Monitor polls in all three skills — which exists because a Monitor can't call MCP tools mid-loop.
  • action-run/action-check need the MCP actions toolset, which the hosted server doesn't enable by default; skills/setup-mcp/mcps.json turns it on with the X-MCP-Toolsets: all header. Per-skill token scopes (repo/workflow, Actions: read/write, Pull requests, etc.) are documented in the README.

Read the full file on GitHub · 42 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 · 42 lines · 826 tokens per session scan A 7db00011e1b9

Subscribe to this mod's changes

devpowers CLAUDE.md is an instructions file published in the GitHub repository kolodkin/devpowers (2 stars, last pushed 23d ago), licensed MIT. It adds 826 tokens to every session, about $0.0041 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

FrontendSecurityWriting and docs
Related

Other instructions, from other repositories

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.

github/spec-kit · 7,104 tokens

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).

microsoft/vscode · 6,785 tokens

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

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.

langchain-ai/langchain · 4,345 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

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