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/component-modelnpx skills add luanmorenommaciel/agentspec --skill component-modelgit 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/component-model)<a href="https://agentmods.dev/skills/luanmorenommaciel/agentspec/component-model"><img src="https://agentmods.dev/badge/skills/luanmorenommaciel/agentspec/component-model.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 | $0.00160 | $0.01616 |
| Opus 5 | $0.00080 | $0.00808 |
| Sonnet 5 | $0.00032 | $0.00323 |
| Haiku 4.5 | $0.00016 | $0.00162 |
Grade A, and why
component-model 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.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Component Model — layer decision and fat-to-thin refactor
The operational side of the repository's component model: place new logic in the right
layer, and pull overgrown components back into theirs. The canonical definitions — the
four layers, the placement table, the thin-executor pattern — live in
.claude/kb/shared/component-model.md; this skill applies that model, it does not
restate it.
When to use
- Deciding whether new functionality should be an agent, a skill, a command, a KB file, or a template.
- Planning a new component before authoring it — the authoring flows load this skill first as their layer-decision gate.
- A component has grown fat — an agent body full of process steps, a command re-implementing methodology inline — and needs restructuring.
- Reviewing a change that spans component types and looks misplaced.
Skip if
- The layer is already decided and you are authoring the component — go straight to
create-skill,create-agent, or/create-kb. - The change is content-only inside an existing component (fixing a step in a skill, updating a KB fact) — no layer question exists.
The decision procedure
-
Read the canonical model. Open
.claude/kb/shared/component-model.md— the four layers, the "where does new logic go" table, and the thin-executor pattern are defined there, and every classification below is grounded in that file. Read it before classifying, not after. -
Classify the new logic. Ask, in order, and stop at the first yes:
- Does it say how to do something — process steps, question frameworks, quality-gate checklists, a verification procedure? → skill.
- Does it define who does the work — identity, tool scope, model tier, stop conditions, escalation targets, non-negotiable policies? → agent (frontmatter plus thin shell).
- Does it define where the user starts — argument surface, mode selection, sequencing of existing pieces? → command.
- Is it a fact other components must agree on — reference truth, standards, domain deep dives? → KB file; if it is an artifact's required shape, it is a template the skill points at.
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.
- 2d ago First seen · 125 lines · 160 tokens per session scan A a49631e8d157
component-model is a skill published in the GitHub repository luanmorenommaciel/agentspec (244 stars, last pushed 3d ago), licensed MIT. It adds 160 tokens to every session and 1,616 once invoked, about $0.0008 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 2026-09-01.
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…