What is skills CLAUDE.md?

A project instruction file that tells the coding agent how to work on the llodev/skills project, including development and release rules.

Use it when developing, validating, or releasing changes to this project’s code, skills, or package adapters.

It gives the agent shared rules for avoiding guesses, limiting changes, checking its work, and releasing updates safely.

skills CLAUDE.md — Instructions file for coding agents by llodev: A project instruction file that tells the coding agent…

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/llodev/skills/claude-md

Clone the repo

git clone --depth 1 https://github.com/llodev/skills

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/llodev/skills/claude-md.svg)](https://agentmods.dev/instructions/llodev/skills/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/llodev/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/llodev/skills/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 782 This file is loaded in full into every session.

When invoked 782 The same file — it is already loaded in full.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5	$0.00782	$0.00782
Opus 5	$0.00391	$0.00391
Sonnet 5	$0.00156	$0.00156
Haiku 4.5	$0.00078	$0.00078

Measured 3d ago against content hash c30a03b6870f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skills 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 3d 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.

CLAUDE.md · 25 lines

How it starts

The opening of the file, as written. The whole thing — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@llodev/skills — agent guide

Universal rules

Don't assume. Don't hide confusion. Surface tradeoffs.
Minimum code that solves the problem. Nothing speculative.
Touch only what you must. Clean up only your own mess.
Define success criteria. Loop until verified.

Dev workflow

make hooks once per clone — installs lefthook (prettier on staged files, gitleaks, Conventional Commits).
make validate after schema, contract, or skill-frontmatter changes (not covered by hooks).
make help lists everything else. Prefer the Makefile over remembering pnpm script names.
Releases: make changeset → make release-version → make release-publish (only when consciously shipping). Each adapter's bin MUST equal the package name and its entry script MUST run unconditionally — lesson from v1.0.1.
make release-version is now gated by make pre-release. If any SKILL.md was modified vs origin/main and scripts/skill-judge-baseline.json was NOT updated, the gate blocks. To proceed: run make skill-judge with current scores, ratchet the baseline if scores improved (Δ ≥ +3), OR bypass with SKIP_SKILL_JUDGE_GATE=1 make release-version when drift is within the noise band ([-2, +2]) — annotate that decision in the changeset summary.
make pre-release also runs the rubric drift gate (unconditionally). This checks that scripts/snapshots/skill-judge-rubric.json still matches the installed ~/.claude/skills/skill-judge/SKILL.md. If it drifts (new dimension, weight change, content edit), the gate blocks. To ratchet: run make skill-judge-rubric-snapshot, review the diff, commit the updated snapshot. The gate is silently skipped when the rubric SKILL.md is not installed (clean clones, CI).

Release convention

One PR = one changeset = one release. Never batch multiple changesets across PRs — changeset version collapses them into a single bump (highest minor wins) and intermediate versions never reach npm. See .changeset/README.md § Release granularity.
Branch naming: pmt-<skill>-v<X.Y.Z>. pmt = project-management-tasks; <skill> = the released package's short name (core, asana, trello, jira, linear, …); <X.Y.Z> = that package's version being released. Examples: pmt-asana-v1.9.0, pmt-trello-v1.8.0, pmt-core-v1.14.0. The skill segment disambiguates the version across packages (asana 1.8.0 and trello 1.8.0 no longer collide as a bare v1.8.0). No feat/ / release/ prefixes and no theme suffixes (-attribution, -hardening) — the SKILL.md / changeset / CHANGELOG already carry the theme.
Hotfix branches: same rule. The branch is pmt-<skill>-v<X.Y.Z> at the patch version (pmt-asana-v1.9.1), not hotfix/<thing>.
PR title: feat(release): <skill> vX.Y.Z — <one-line theme> (skill + version + theme in the title).

Read the full file on GitHub · 25 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.

3d ago First seen · 25 lines · 782 tokens per session scan A c30a03b6870f

Subscribe to this mod's changes

skills CLAUDE.md is an instructions file published in the GitHub repository llodev/skills (2 stars, last pushed 2d ago), licensed MIT. It adds 782 tokens to every session, about $0.0039 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 2026-08-31.

Git and workflow Productivity agent-skills ai ai-agents automation claude claude-code

finding-unknowns-skills CLAUDE.md

Claude Code instructions for Neeeophytee/finding-unknowns-skills, covering repo notes, what ships, and the gate that decides, version lives in three manifests — move them together, files that must be edited together and shipped guidance is not this file.

Neeeophytee/finding-unknowns-skills · 1,447 tokens

skills CLAUDE.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

@llodev/skills — agent guide

Universal rules

Dev workflow

Release convention

What this file has done since we first saw it

Other instructions, from other repositories

finding-unknowns-skills CLAUDE.md

humansintheloop-dev-workflow-and-tools CLAUDE.md

omnifocus-claude-extension CLAUDE.md

VoxClaw AGENTS.md

vidcraft CLAUDE.md

agent-hive hive-workflow.instructions.md