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 jscraik/Agent-Skills --skill skill-refactorgit clone --depth 1 https://github.com/jscraik/Agent-SkillsWrote 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/jscraik/agent-skills/skill-refactor)<a href="https://agentmods.dev/skills/jscraik/agent-skills/skill-refactor"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/skill-refactor/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/jscraik/agent-skills/skill-refactor"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/skill-refactor.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 | $0.00081 | $0.02552 |
| Opus 5.5 | $0.00032 | $0.01021 |
| Sonnet 5.5 | $0.00016 | $0.00510 |
| Haiku 4.5 | $0.00008 | $0.00255 |
Grade A, and why
skill-refactor 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 1mo 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Refactor
Analyze bounded evidence about skill reliability and turn it into a lifecycle decision or a repair handoff.
Philosophy
Decide from bounded evidence; prefer narrow, reversible lifecycle moves.
First-Principles Gate
- Desired outcome: classify skill reliability evidence and route to keep, observe, improve, capture, merge/fold with approval, or retire with approval without mutating source prematurely.
- User-specific constraints: use bounded evidence, preserve approval boundaries, route improvements through Skill Factory hardening, and map eval disagreement to SDK gates.
- Rejected copied assumption: a failing skill should immediately be rewritten or retired.
- Fundamental constraints: evidence strength controls scope; lifecycle decisions need approval when destructive; weak evidence cannot justify broad canonical changes.
- Smallest effective mechanism: produce a lifecycle decision and concrete repair handoff items before edits.
- Artifact decision: IMPROVE_EXISTING.
- Rejected alternatives: retiring from weak evidence, merging without approval, or patching source before classifying root cause.
- Evidence required: evidence anchors, root-cause labels, and repair items with expected SDK gate.
- Validation proof: each finding cites one source and one owning gate.
- Stop or pivot condition: if evidence is missing or untrusted, ask for bounded evidence instead of recommending a lifecycle move.
When To Use
- The user asks which skill is failing, why a skill keeps producing bad outcomes, or whether a skill should be kept, improved, merged, split, retired, or observed.
- Evidence exists from session collector, Tessl review, Plugin Eval, validation logs, evals, CodeRabbit/Codex findings, or review artifacts.
- The expected output is analysis and routing, not direct source edits.
Do Not Use When
- New skill creation ->
skillifyorskill-creator. - Hardening a known existing skill -> Skill Factory hardening workflow.
- Install, sync, publish, or runtime projection mutation.
- Evidence is missing, untrusted, too broad, or requires external/destructive action.
What ships with it
13 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.
- .skillignore 20 B
- agents/assets/icon-large.png 22 KB
- agents/assets/icon-small.png 2.6 KB
- agents/openai.yaml 224 B
- assets/skill-refactor.png 7.2 KB
- references/contract.yaml 5.5 KB
- references/discovery-interview.md 3.5 KB
- references/evals.yaml 20 KB
- references/evidence-routing.md 1.5 KB
- references/harness-evidence-mapping.md 1.2 KB
- references/task-profile.json 1.2 KB
- references/taxonomy.md 1.5 KB
- scripts/README.md 259 B
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.
- 1mo ago Changed · +217 lines · +37 tokens per session 20552717da7d
- 1mo ago First seen · 13 lines · 44 tokens per session scan A f7b9134bc16d
skill-refactor is a skill published in the GitHub repository jscraik/Agent-Skills (9 stars, last pushed 4d ago), licensed Apache-2.0. It adds 81 tokens to every session and 2,552 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
worker-integration
Worker-Agent integration for intelligent task dispatch and performance tracking.
agui-dotnet-streaming-chat
Get started with the AG-UI .NET SDK: bootstrap and run your first streaming-chat app (client + server) with the AG-UI .NET NuGet packages (AGUI.Client, AGUI.Server, AGUI.Formatting, AGUI.Abstractions). USE FOR: which packages to install and how to wire them; constructing an AGUIChatClient against an endpoint and…
agui-dotnet-protobuf
Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
moai-ref-ui-polish
UI polish and interface-completion reference: the small visual details — concentric border radius, optical alignment, shadow-vs-border, motion easing, typography smoothing, tabular numbers, icon stroke weight, hit areas — that separate polished interfaces from generic ones. Agent-extending skill that amplifies…