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.
npx skills add komluk/scaffolding --skill skill-authoringgit clone --depth 1 https://github.com/komluk/scaffoldingWrote 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/komluk/scaffolding/skill-authoring)<a href="https://agentmods.dev/skills/komluk/scaffolding/skill-authoring"><img src="https://agentmods.dev/badge/skills/komluk/scaffolding/skill-authoring.svg" alt="Measured on agentmods" 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 | $0.00076 | $0.02075 |
| Opus 5 | $0.00038 | $0.01038 |
| Sonnet 5 | $0.00015 | $0.00415 |
| Haiku 4.5 | $0.00008 | $0.00208 |
Grade A, and why
skill-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 6d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Authoring Skill
Purpose
Methodology for authoring scaffolding-compatible skills. A skill is a single
SKILL.md file under skills/<name>/ that encodes a reusable methodology Claude
Code can auto-invoke. This skill defines the frontmatter contract, the recommended
body structure, the description-writing rules, and the quality bar every authored
skill must meet before it ships.
When to Apply
Apply this skill when:
- Running the
/create-skillcommand to scaffold a new skill - Hand-writing or editing a
skills/<name>/SKILL.mdfile - Reviewing a skill for frontmatter correctness or auto-invocation quality
- Deciding whether a repeatable procedure deserves promotion into its own skill
Do NOT apply this skill for:
- Distilling a conversation into knowledge candidates — use
distill - Writing into the 3-tier file memory — use
agent-memory
Frontmatter Contract
Every SKILL.md MUST begin with a YAML frontmatter block delimited by ---:
| Field | Rule |
|---|---|
name |
Required. Kebab-case ^[a-z][a-z0-9-]*$. MUST equal the parent directory name. |
description |
Required. Non-empty, 1–340 characters. Follows the Description Contract below. |
context |
Optional. Only value: fork — run the skill in an isolated forked subagent. See "Context: fork". |
agent |
Optional. Sub-agent for a forked skill: Explore, Plan, or general-purpose. |
effort |
Optional. Reasoning-effort hint: low, medium, or high. |
name and description are the only required fields. context, agent,
and effort are optional delivery-tuning fields. All five are value-checked by
validators/validate-skill.sh; any other frontmatter key is left untouched.
Description Contract
The description field drives Claude Code's automatic skill invocation. A vague
or overbroad description either fails to trigger or triggers on the wrong tasks.
Every scaffolding skill description MUST follow this template:
"<one-line capability summary>. TRIGGER when: <2-4 concrete observable situations>. SKIP: <1-2 cases handled by a named neighbour skill or out of scope>."
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.
- 6d ago First seen · 182 lines · 76 tokens per session scan A 32b0af012aa0
skill-authoring is a skill published in the GitHub repository komluk/scaffolding (15 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 2,075 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
turnstile-loop-start
Starts a goal-directed loop run -- asks for mode, initialises state.json, then dispatches loop-runner repeatedly until the success condition is met, max-iterations is reached, or an unrecoverable error occurs.
turnstile-loop-status
Reads turnstile/loops/ /state.json and renders the current phase, status, and full iteration history in the terminal.
turnstile-conversate
Entry point for natural-language turnstile requests -- classifies the message against board state, then answers directly or invokes the one matching skill (brainstorm, quick, refine, spec, sprint-plan, work, review, breakdown, drop, systematic-debugger, code-reviewer).
turnstile-work
Implements one sprint ticket via TDD and the turnstile-coder agent, checking the brain first. Dispatched by /turnstile:work or conversate routing only.
turnstile-brain-init
Opt-in bulk bootstrap of turnstile/code/ -- one linked note per source file. The default pipeline is lazy (code notes only for ticket-touched files, written when the ticket passes review); this is the eager exception. Dispatched by /turnstile:brain-init only.
turnstile-brain
Vault layout, the shared note format, and the check-the-brain-first mandate. Auto-loads whenever any turnstile skill starts new work or /turnstile:review is about to commit.