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 skilletmd/skillet --skill skillet-routegit clone --depth 1 https://github.com/skilletmd/skilletWrote 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/skilletmd/skillet/skillet-route)<a href="https://agentmods.dev/skills/skilletmd/skillet/skillet-route"><img src="https://agentmods.dev/badge/skills/skilletmd/skillet/skillet-route/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/skilletmd/skillet/skillet-route"><img src="https://agentmods.dev/badge/skills/skilletmd/skillet/skillet-route.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00080 | $0.00779 |
| Opus 5 | $0.00040 | $0.00390 |
| Sonnet 5 | $0.00016 | $0.00156 |
| Haiku 4.5 | $0.00008 | $0.00078 |
Grade A, and why
skillet scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skillet route (/skillet)
Look at the first token after /skillet, call one verb, and follow the
instructions it returns. Each verb answers with its data AND the rules for that
path, so everything you need arrives with the call. Nothing below is the whole
flow; the verb's response is.
Branch on the first token
create is a verb, not a handle. (/skillet create, /skillet create a skill for our deploy ritual.) Load the bundled @skillet/create playbook
and follow it instead of routing. Run no verb, no phases, and no record. It sits
in two places; read whichever exists:
- The sibling
skillet-create/SKILL.mdnext to this file.skillet initwrites both together, so this is the copy an anonymous install has. ~/.skillet/skills/@skillet/create/SKILL.md, or$SKILLET_DIR/skills/..., once the machine has synced.
It is deliberately absent from routing candidates: the CLI's own meta-skills are
never routed to, so a path is how you reach it. If neither copy exists, say so in
one line and run skillet init to install it rather than improvising a create
flow of your own.
A handle (/skillet @mattpocock review my PR, or the same without the @)
routes against that person's public kit, fetched live. No install, no sync, no
account:
skillet route summon <handle>
Anything else is a task for the user's own kit:
skillet route start
If a hook already placed kit candidates in your context, skip start and go
straight to picking from those.
Then load what you picked
skillet route use <ref>
Add --hash <hash> --via <handle> when the candidate came from summon, using
the values that candidate carried. This is the only call that loads a body, and
it records the route, so never call skillet route begin or
skillet route record yourself.
Over MCP
When the connected surface exposes summon, search_public, and a skill reader,
use those tools instead of shelling out. Same attribution and the same consent
rules either way. One difference binds only there: call the summon-marked read
at most once per invocation, since the CLI's single-loader guarantee does not
reach across that boundary.
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.
- 11d ago First seen · 77 lines · 80 tokens per session scan A 87028dcbd077
skillet is a skill published in the GitHub repository skilletmd/skillet (3 stars, last pushed 12d ago), licensed Apache-2.0. It adds 80 tokens to every session and 779 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 2026-08-31.
Other skills, from other repositories
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
requirements-authoring
To author, update, and validate functional/non-functional requirements as atomic units with user approval.
specflow-use
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.
ijfw-workflow
Use when the user says: 'build', 'create', 'plan', 'new project', 'brainstorm', 'design', 'UI', 'website', 'dashboard', 'app', 'help me build', 'launch', 'book', 'campaign', or anything project-level. Skill body decides Quick vs Deep path.
ijfw-plan
Use when the user says 'plan this', 'plan it', 'make a plan', 'let's plan', 'draft a plan', 'how should we tackle this', 'break this down', or invokes '/ijfw-plan'. Produces a falsifiable PLAN.md (software, book, campaign, design, research) with task breakdown, dependency wave-table, and success criteria — gated by…
ijfw-writing-skills
Authoring discipline for new IJFW skills. Use when creating a new skill, writing a skill, making a skill that does X, or asked to add a skill. Trigger: create a new skill, write a skill, new skill, make me a skill, skill that does, /ijfw-writing-skills.