darwin-skill

An autonomous tool for evaluating and improving SKILL.md files, which are instruction files for coding-agent skills. It uses a nine-part review rubric, validation checks, and human approval points.

In plain words
What is it for?
It is for reviewing skill structure and effectiveness, validating changes to SKILL.md files, and optimizing agent-skill instructions with human checkpoints.
Why use it?
It helps identify weaknesses in skill instructions and requires validation before proposed improvements are accepted.

Skill for Claude CodeCodex

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 skills/sxxpqp/linux/darwin-skill
Any agent
npx skills add sxxpqp/linux --skill darwin-skill
Clone the repo
git clone --depth 1 https://github.com/sxxpqp/linux

Made for: Claude Code, Codex.

Per session 195 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,453 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00195 $0.07453
Opus 5 $0.00097 $0.03726
Sonnet 5 $0.00039 $0.01491
Haiku 4.5 $0.00019 $0.00745

Measured 3d ago against content hash b4597b0fb789, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

darwin-skill 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.

.agents/skills/darwin-skill/SKILL.md · 487 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. 3d ago First seen · 487 lines · 195 tokens per session scan A b4597b0fb789

Subscribe to this mod's changes

darwin-skill is a skill published in the GitHub repository sxxpqp/linux (5 stars, last pushed 9d ago), with no licence file. It adds 195 tokens to every session and 7,453 once invoked, about $0.0010 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.

Related

Other skills, from other repositories

docker-wizard

Generate optimized Dockerfiles and docker-compose.yml with best practices and multi-stage builds.

glincker/claude-code-marketplace · 19 tokens

container-manager-kubernetes-operations

Full operational Kubernetes surface via the container-manager-mcp MCP server — workloads (pods/rollouts/StatefulSets/DaemonSets/ReplicaSets/Jobs/CronJobs), config (ConfigMaps/Secrets/Namespaces/CRDs/patch), networking (Ingress/native Services/NetworkPolicy/DNS), storage (PV/PVC/StorageClass/snapshots/CSI), RBAC…

Knuckles-Team/container-manager-mcp · 189 tokens

docker-docs

Comprehensive Docker 28.x reference covering all features: installation, Dockerfile instructions, multi-stage builds, Docker Compose, networking, volumes, CLI commands, image management, registries, security best practices, CI/CD integration, debugging, and Kubernetes migration. Use whenever the user mentions Docker…

pledgeandgrow/pledge-skills · 93 tokens

docker

Operational skill for Claude to automate Docker via CLI, Dockerfiles, Compose, BuildKit, multi-stage builds, and container networking hygiene.

alivirgo/Major-AI-Skills · 29 tokens

docker-agent

Write optimized Dockerfiles, docker-compose configs, and debug container issues. Use when containerizing an app, fixing a broken container, or designing a multi-service local environment.

chandrudp29/skillhub · 37 tokens

dockerfile-python-app

Write an efficient, secure Dockerfile for a Python app — layer caching, slim images, non-root user, and healthchecks.

vikasudasi/skill-vault · 31 tokens