skill-authoring

A set of admission and structure rules for writing reusable skills—step-by-step instructions an agent can apply to recurring work.

In plain words
What is it for?
Use it when creating or changing a skill, including its metadata, allowed tools, iteration limits, references, and inventory entry in AGENTS.md.
Why use it?
It helps keep the skill library small, consistent, and easy to find. It also prevents adding one-off instructions or duplicating an existing skill.

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/doidor/agentrig/skill-authoring
Any agent
npx skills add doidor/agentrig --skill skill-authoring
Clone the repo
git clone --depth 1 https://github.com/doidor/agentrig

Made for: Claude Code, Codex.

Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 428 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00024 $0.00428
Opus 5 $0.00012 $0.00214
Sonnet 5 $0.00005 $0.00086
Haiku 4.5 $0.00002 $0.00043

Measured 2d ago against content hash f8033555e65c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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/skill-authoring/SKILL.md · 36 lines

What it actually says

skill-authoring (principle 4, 8)

Skills are procedural memory. A bloated skill library is as useless as no library, so new skills must clear an admission bar.

Admission test (all must hold)

  1. Reusable, not one-off. It encodes how to do one recurring thing well — not a single task.
  2. Not already covered. Search .agents/skills/; if an existing skill is close, sharpen it instead of adding a near-duplicate.
  3. A procedure, not a reflex. Passive, always-on constraints belong in .agents/rules/, not a skill.

Structure

  • SKILL.md with YAML frontmatter: name, a description < 250 chars, triggers, allowed-tools (scope the blast radius), and an optional argument-hint.
  • Body: short, imperative steps. Cap iteration loops and state the fallback.
  • Put long reference material in a sibling references/ file and link to it, so the skill itself stays small and the agent loads detail only on demand.
  • Scope allowed-tools to the minimum (e.g. Bash Read Grep Glob).

Keep surfaces in sync

When you add or remove a skill, update the skills inventory in AGENTS.md (the AGENTRIG:skills-inventory block) so every surface advertises the same set. If the repo mirrors skills across vendor dirs (.claude/.copilot/.agents/…), they should all point at one canonical source (AgentRig wires these as symlinks).

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. 2d ago First seen · 36 lines · 24 tokens per session scan A f8033555e65c

Subscribe to this mod's changes

skill-authoring is a skill published in the GitHub repository doidor/agentrig (5 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 428 once invoked, about $0.0001 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens