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/pradeepmouli/skillit/skillit-refinenpx skills add pradeepmouli/skillit --skill skillit-refinegit clone --depth 1 https://github.com/pradeepmouli/skillitWrote 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/pradeepmouli/skillit/skillit-refine)<a href="https://agentmods.dev/skills/pradeepmouli/skillit/skillit-refine"><img src="https://agentmods.dev/badge/skills/pradeepmouli/skillit/skillit-refine.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 5.1 | $0.00047 | $0.00433 |
| Opus 5 | $0.00023 | $0.00217 |
| Sonnet 5 | $0.00009 | $0.00087 |
| Haiku 4.5 | $0.00005 | $0.00043 |
Grade A, and why
skillit-refine 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 6d 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.
What it actually says
skillit-refine
Autonomously improve an MCP skill via the skillit audit→draft→review loop (build or runtime mode)
Commands
refine
Autonomously improve a skill via the audit→draft→review loop
Usage:
[options]
| Flag | Type | Required | Default | Env | Description |
|---|---|---|---|---|---|
--mcp |
string |
yes | — | — | path to mcp.json or MCP config file |
--server |
string |
no | — | — | server name within the config (defaults to first enabled) |
--overlay |
string |
no | — | — | path to overlay JSON file (runtime mode only) |
--mode |
string |
no | — | — | refine mode: build or runtime (auto-detected if omitted) |
--source-glob |
string |
no | — | — | glob pattern for TypeScript source files (build mode) |
--max-iterations |
string |
no | 5 |
— | iteration cap (default 5) |
--items |
string |
no | 5 |
— | work items per iteration (default 5) |
References
Load these on demand — do NOT read all at once:
- When using CLI commands → read
references/commands.mdfor flags, arguments, and defaults
Links
What ships with it
1 file 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.
- 6d ago First seen · 41 lines · 47 tokens per session scan A 6249fc3d18d8
skillit-refine is a skill published in the GitHub repository pradeepmouli/skillit (7 stars, last pushed 20d ago), licensed MIT. It adds 47 tokens to every session and 433 once invoked, about $0.0002 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
release
Prepare and publish Perigon.CLI patch releases, including versioning, release notes, bilingual docs, validation, and the nuget-branch CI handoff.
docs
Use for Perigon documentation work across this workspace, especially Perigon.docs/Content/docs/Perigon bilingual and versioned docs, syncing zh-CN and en-US content, updating docs from Perigon.CLI, Perigon.template, and Perigon.Modules changes, and deciding whether to revise existing pages or add new documentation.
blazor
Use for Blazor Server development with Fluent UI Blazor, Razor components, layouts, pages, scoped UI services, culture switching, localization, forms, loading/empty/error states, and Studio-style dashboard workflows.
cli
Use for .NET command-line tool development with Spectre.Console/Spectre.Console.Cli, Microsoft.Extensions.Hosting, dependency injection, localized help text, command settings, aliases, examples, terminal output, exit codes, and stdio-safe command paths.
codegen
Use for .NET code generation work with Roslyn, Microsoft.OpenApi, Razor templates, DTO/manager/controller generation, REST API generation, C# HttpClient generation, Angular/Axios TypeScript request clients, generated formatting, and deterministic output.
dotnet
Use for .NET application development involving services, managers, dependency injection, Microsoft.Extensions.Hosting, dependency direction, MiniDb persistence, DTOs, Mapster mapping, shared entities/helpers, MCP tools, module workflows, solution analysis, cancellation, logging, and logic shared by CLI and Blazor.