Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/shennawardana23/skillmenpx agentmods add skills/shennawardana23/skillme/skill-catalog-authoringWrote 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.
[](https://agentmods.dev/skills/shennawardana23/skillme/skill-catalog-authoring)<a href="https://agentmods.dev/skills/shennawardana23/skillme/skill-catalog-authoring"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/skill-catalog-authoring/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/shennawardana23/skillme/skill-catalog-authoring"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/skill-catalog-authoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00096 | $0.01892 |
| Opus 5 | $0.00048 | $0.00946 |
| Sonnet 5 | $0.00019 | $0.00378 |
| Haiku 4.5 | $0.00010 | $0.00189 |
Grade A, and why
skill-catalog-authoring 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Catalog Authoring
This plugin (skillme) is a catalog of Claude Code skills, each shipped
with an eval suite graded by smeval — this repository's own eval runner
(cmd/smeval, plain Go, no third-party dependency) — so a skill's quality
is measurable and re-checked in CI on every change, rather than trusted on
first impression. smeval follows Anthropic's documented Agent Skills
evaluation methodology (https://agentskills.io/skill-creation/evaluating-skills):
a prompt and assertions per case, graded with concrete evidence. Follow this
process whenever adding a skill to skills/ or modifying an existing one's
evals/.
Directory layout for a new skill
skills/<skill-name>/
├── SKILL.md # required
├── references/ # optional — detailed docs loaded only when needed
├── examples/ # optional — working code examples
└── evals/
└── evals.json # required — smeval's case file for this skill
Use kebab-case for <skill-name>. evals.json's top-level skill_name
must match the directory name exactly — smeval validate rejects a
mismatch.
SKILL.md conventions
Frontmatter follows the official spec at https://agentskills.io/specification
exactly — the fields below are the only ones a validator will accept;
anything else (including a bare top-level version:) is rejected:
| Field | Required | Constraint |
|---|---|---|
name |
Yes | 1–64 chars, lowercase unicode alphanumeric + hyphens, no leading/trailing/double hyphen, must equal the directory name exactly |
description |
Yes | 1–1024 chars. Third person ("This skill should be used when the user asks to..."), packed with concrete quoted trigger phrases, not a vague topic label |
license |
No | Short license name or reference to a bundled LICENSE |
compatibility |
No | 1–500 chars. Only include if there's a real environment requirement (e.g. "Requires Go 1.26+ and google.golang.org/adk/v2") |
metadata |
No | String→string map for anything else — this is where version goes (metadata: { version: "0.1.0" }), never as a bare top-level field |
allowed-tools |
No | Space-separated pre-approved tools (experimental, client-dependent) |
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 160 lines · 96 tokens per session scan A 155cf5de472a
skill-catalog-authoring is a skill published in the GitHub repository shennawardana23/skillme (2 stars, last pushed 14d ago), licensed Apache-2.0. It adds 96 tokens to every session and 1,892 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code.
fix-bug
Resolves a single bug from any starting evidence — Dash0 telemetry (span / log / web event / RUM error link), raw stack trace, error message, code pointer (file:line), screen recording, Linear ticket URL, or free-text symptom. Classifies the input, triages complexity (Phase 0.5) to pick between a fast lane and a full…
storybook
Scaffolds, audits, and tests Storybook stories for React (web) and React Native / Expo (native) component libraries. Generates three artefacts in two files per invocation: a visual regression .stories.tsx file containing a Default story (variants grouped into a single snapshot) and a Playground story (interactive args…
aw-setup
One-time (but safely re-runnable) setup flow that scaffolds a project's aw-tester aw-target: detects auth strategy, captures storage state, writes .claude/aw-targets/local.yml, and validates with a smoke spec. Re-runs detect the existing aw-target and only re-prompt for what broke or changed. Triggers on "/aw-setup"…
aw
Ships autonomous, end-to-end coding work — implement a feature or fix, all the way to a tested draft PR — from a single opt-in entry point. Detects the task tier (Micro / Lite / Full) and routes: Micro/Lite run single-pass in this context; Full hands off to the aw-planner → aw-executor agents. Use when the user asks…
polish
Re-runnable pre-PR quality gate for the current branch. Composes two existing passes over the branch diff: a broad pr-reviewer pass (read-only review via the branch's open PR, which pr-reviewer requires) and a code-quality simplify pass (applies Class M mechanical refactors behind a confidence ≥ 90 % gate, reverting…