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/fledgeling-co/fledgeling-plugins/create-skillnpx skills add fledgeling-co/fledgeling-plugins --skill create-skillgit clone --depth 1 https://github.com/fledgeling-co/fledgeling-pluginsWrote 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/fledgeling-co/fledgeling-plugins/create-skill)<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/create-skill"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/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 | $0.00235 | $0.03124 |
| Opus 5 | $0.00118 | $0.01562 |
| Sonnet 5 | $0.00047 | $0.00625 |
| Haiku 4.5 | $0.00023 | $0.00312 |
Grade A, and why
create-skill 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 4d 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
create-skill
Build a skill that does not exist yet, properly: understand what the user actually wants before writing anything, ground the design in evidence rather than instinct, prove it works against the honest baseline of not having it, and ship it like a product.
The sibling of improve-skill. That one starts from an artifact and its
failures; this one starts from an intention, which is harder, because an
unstated intention is the most common reason a new skill misses. So this
pipeline front-loads the interview and treats a vague answer as a defect
to fix rather than a constraint to work around.
Running as a Gemini model? Read gemini.md in this directory first, then follow this file with the overrides it names. Turns Phase 2's traceability rule and Phase 5's banner-through-design-craft into a filled ledger and file-gated phases, restores the verification scaffolding the Opus brief file strips, and names the four deliverables to hand to another model. Other models skip it.
Phase 0 — Discovery (the phase that decides everything)
A new skill has no predecessor to argue with, so the brief is the only
specification. Get it right before anything else runs. Full protocol:
references/discovery.md.
The short version:
- Answer what you can from what you already have. The conversation, the repo, sibling skills, an earlier subagent's findings, a failed workflow's output. A question whose answer is already on disk wastes the user's attention and makes the rest look less considered.
- Then ask, with recommendations. Use AskUserQuestion, multi-choice where the options are genuinely discrete, each option carrying what it means and what it costs. Lead with the one you would pick and say why. Users answer a recommendation faster than an open question, and a recommendation they reject is itself information.
- Cover the axes a skill actually turns on: what triggers it, what it produces, who reads the output, what "done" looks like, what it must never do, whether outputs are objectively checkable, and what existing tools or skills it should route to rather than reimplement.
- Leave room for notes. Every question invites free text alongside the choice; the notes are where the real constraint usually appears.
What ships with it
8 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.
- 4d ago First seen · 250 lines · 235 tokens per session scan A 510f6472e3f1
create-skill is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed today), licensed MIT. It adds 235 tokens to every session and 3,124 once invoked, about $0.0012 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.
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…