alexmskills: Instructions file for Claude Code

CLAUDE.md

alexmskills CLAUDE.md is an instructions file for Claude Code from alexmond/alexmskills. It costs 5,725 tokens per session, scanned B, original, MIT.

A project instruction file for alexmskills, a collection of reusable Claude Code skills and agents. It explains the project's folders, plugin catalog, conventions, and validation tools.

In plain words
What is it for?
Use it when adding, updating, validating, or documenting plugins, skills, agents, and hooks in the alexmskills project.
Why use it?
It helps coding agents understand how the marketplace is organized and how its plugins should be maintained consistently.

Instructions file for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is alexmond/alexmskills's own configuration. It tells Claude Code how to work on alexmskills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything alexmskills configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

Reuse

Borrowing it

Nothing to install: this file belongs to alexmond/alexmskills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/alexmond/alexmskills/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/alexmond/alexmskills

Made for: Claude Code.

Wrote 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.

agentmods badge for alexmskills CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/alexmond/alexmskills/claude-md.svg)](https://agentmods.dev/instructions/alexmond/alexmskills/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/alexmond/alexmskills/claude-md"><img src="https://agentmods.dev/badge/instructions/alexmond/alexmskills/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 5,725 This file is loaded in full into every session.
When invoked 5,725 The same file — it is already loaded in full.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.05725 $0.05725
Opus 5 $0.02863 $0.02863
Sonnet 5 $0.01145 $0.01145
Haiku 4.5 $0.00573 $0.00573

Measured yesterday against content hash 1133aea715f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

alexmskills CLAUDE.md scanned grade B 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

`~/.claude/settings.json`), so this repo's hooks run the *installed* build, not `plugins/` — test
CLAUDE.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

alexmskills

A public Claude Code plugin marketplace of reusable, self-improving skills and agents. Each skill is an independently versioned plugin. This file is the project's working memory; the README is the public front door.

Layout

.claude-plugin/marketplace.json   # the catalog — every plugin + its source/version
plugins/<name>/                   # one directory per plugin
  .claude-plugin/plugin.json      #   manifest (name, version, author, …)
  skills/<skill>/SKILL.md         #   one or more skills
  agents/<agent>.md               #   subagents (review-agents, dev-crew)
  hooks/hooks.json                #   plugin-shipped hooks (evolving-claude-md)
docs/                             # Antora component → published at alexmond.org/alexmskills
scripts/validate-marketplace.sh   # jq-based validator (also run in CI)
Makefile                          # validate / list / bump helpers
.claude/                          # per-plugin state (mindmap, prompt-coach, skill-linter)

Catalog (see README for descriptions)

evolving-claude-md, memory-hygiene, dev-crew, brainstorm-panel, learn-on-failure, roles, prompt-coach (self-learning) · implement-issue, maven-quality, security-audit, screenshot-tour, progress-channel, ticket-triage (workflow) · review-agents (review) · research-sweep (research) · skill-linter (self-learning). Beta (-beta suffix): tune-repo-beta, systemic-fix-beta.

Conventions

  • One skill = one plugin, unless skills are tightly coupled (then bundle + version them together, like maven-quality). This is what makes per-skill versioning possible at all.
  • Every plugin.json carries the same metadata shape: name, description, version (semver), author (Alex Mondshain / [email protected]), homepage, repository, license: MIT, keywords. The name MUST match its marketplace.json entry.
  • Bump versions with make bump PLUGIN=<n> VERSION=<x.y.z> so plugin.json and marketplace.json never drift. Validate with claude plugin tag --dry-run plugins/<n>.
  • Run make validate before committing. CI runs it too.
  • Skills must be project-agnostic. No hardcoded absolute paths, usernames, or repo names — these are pulled FROM other repos and generalized; keep them that way.
  • Docs are part of "done": a new plugin needs a docs/modules/ROOT/pages/<n>.adoc page, a nav.adoc entry and a row on index.adoc; every version bump gets a CHANGELOG.md entry (grouped by date, tagged with plugin + version). make validate enforces all three — it was a convention until the landing page drifted four plugins behind the catalog.
  • Plugin naming: orchestrators are <scope>-<team-noun>, the team-noun encoding coordination (crew = handoff/deliver, panel = debate/decide, sweep = fan-out/discover); other skills are descriptive kebab-case, verb-first for actions, ≤3 words, no redundant qualifiers.
  • Role naming: a role is named for the persona (a noun — who they are), never the task (a verb — what they do), so it reads right seated solo, in a crew, on a panel, or in a sweep. Coverage roles use <dimension>-scout. Role names are shared across orchestrators (one skeptic, one architect).
  • Never push or cut release tags without explicit user confirmation.
  • Attribution: all plugins are original work by the author (MIT, per plugin.json author); the roles-plugin personas credit @nahidulislam404's prompt thread as inspiration. This is a public-repo provenance note; don't drop it in a cleanup.

Read the full file on GitHub · 150 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 Changed · +2 lines · +155 tokens per session 1133aea715f7
  2. 8d ago First seen · 148 lines · 5,570 tokens per session scan B 60c4b97a0d80

Subscribe to this mod's changes

alexmskills CLAUDE.md is an instructions file published in the GitHub repository alexmond/alexmskills (6 stars, last pushed today), licensed MIT. It adds 5,725 tokens to every session, about $0.0286 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

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 · 5,153 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

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.

vercel/next.js · 7,296 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 · 4,469 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

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