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 agentmods add skills/luanmorenommaciel/agentspec/create-skillnpx skills add luanmorenommaciel/agentspec --skill create-skillgit clone --depth 1 https://github.com/luanmorenommaciel/agentspecWrote 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/luanmorenommaciel/agentspec/create-skill)<a href="https://agentmods.dev/skills/luanmorenommaciel/agentspec/create-skill"><img src="https://agentmods.dev/badge/skills/luanmorenommaciel/agentspec/create-skill.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 | $0.00168 | $0.01179 |
| Opus 5 | $0.00084 | $0.00589 |
| Sonnet 5 | $0.00034 | $0.00236 |
| Haiku 4.5 | $0.00017 | $0.00118 |
Grade A, and why
create-skill scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. **Fetch the upstream methodology directly** — it is public. Retrieve `https://raw.githubusercontent.com/anthropics/skills/main/skills/skill-creator/SKILL.md` (web fetch or `curl`) and follow it as if the skill were in How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a Skill (repo conventions)
Author the skill itself with Anthropic's upstream skill-creator skill where it is installed — it owns the general methodology (structure, description writing, progressive disclosure, packaging, evals). This skill carries only what skill-creator cannot know: this repository's conventions and build pipeline. Do not duplicate the upstream methodology here or in the skills you write.
Before authoring anything, confirm a skill is the right layer: run the component-model skill (canonical model: .claude/kb/shared/component-model.md). Many "new skill" asks turn out to be commands, KB content, or a thin agent plus an existing skill.
Division of labor
| Concern | Owner |
|---|---|
| Skill structure, description craft, progressive disclosure, packaging, evals | skill-creator (upstream) — invoke it when available, fetch it when not |
| Naming, placement, frontmatter pitfalls, ship checklist | this skill |
When skill-creator is not installed, fall back in order:
- Fetch the upstream methodology directly — it is public. Retrieve
https://raw.githubusercontent.com/anthropics/skills/main/skills/skill-creator/SKILL.md(web fetch orcurl) and follow it as if the skill were installed; it references sibling files under the same directory that can be fetched the same way when needed. - Offline as well? Three principles carry most of its weight: one skill = one capability (split when triggers stop being related); the
descriptionis the entire trigger mechanism (what it does + when to use it + one "do not use for" boundary, third person, ≤1024 chars); keep SKILL.md under ~500 lines and push detail intoreferences/(read on demand),scripts/(deterministic helpers), andassets/(files used in output).
Repo conventions
- Naming. Kebab-case, at least one hyphen,
namefield == folder name. Prefer domain-verb or domain-noun compounds (kb-build,github-post-issue,meeting-analysis). Avoid noise words (helper,tool,utils, a-skillsuffix) and avoid-eragent-style names for skills — those read as agent roles. - Placement. Three tiers:
- Distributed skill →
.claude/skills/<name>/; the build mirrors it intoplugin/skills/. - Plugin-only skill →
plugin-extras/skills/<name>/; merged in at build, absent from.claude/. - Repo-local skill (for contributors of this repository, not distributed) →
.claude/skills/<name>/plus an entry in theREPO_LOCAL_SKILLSexclusion list inbuild-plugin.sh.
- Distributed skill →
- Frontmatter. Only supported keys (
name,description, optionallylicense,allowed-tools,metadata,compatibility). YAML traps that fail silently: a#inside an unquoted value truncates it; a:inside an unquoted value breaks parsing; write multi-line descriptions as a literal block (|). Never invent keys — there is notriggers:field; the description IS the trigger. - Internal paths. Reference
.claude/kb/...,.claude/skills/...,.claude/agents/...normally — the build rewrites them to plugin paths..claude/sdd/workspace paths (drafts/,features/,reports/,archive/) are preserved as-is by design.
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 · 54 lines · 168 tokens per session scan A 3fc1c0bc8fa3
create-skill is a skill published in the GitHub repository luanmorenommaciel/agentspec (244 stars, last pushed yesterday), licensed MIT. It adds 168 tokens to every session and 1,179 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
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.
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.
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.
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…