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-factory-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-factory-skill-refactor)<a href="https://agentmods.dev/skills/jscraik/agent-skills/skill-factory-skill-refactor"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/skill-factory-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-factory-skill-refactor"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/skill-factory-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 | $0.00044 | $0.00892 |
| Opus 5 | $0.00022 | $0.00446 |
| Sonnet 5 | $0.00009 | $0.00178 |
| Haiku 4.5 | $0.00004 | $0.00089 |
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 12d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Refactor
Analyze skill reliability from session evidence and return prioritized recommendations.
Read when: evidence schema or audit criteria are needed: contract Read when: session history must be inventoried or extracted before synthesis: session evidence workflow
Philosophy
- Evidence first: recommendations must be traceable to concrete session artifacts.
- Favor high-leverage fixes that reduce repeated failures across multiple skills.
- Keep recommendations executable by mapping each finding to a clear next action.
When to use
- Use when the user asks for evidence-backed skill reliability analysis from session history.
- Use when deciding whether to install, improve, merge, or retire skills.
Required inputs
- A clear analysis scope (single skill, category, or full inventory).
- Session evidence sources or local artifacts available for review, preferably a
~/.agents/session-collectorbundle for broad session scope. - Ranking criteria for severity and impact.
Deliverables
- Prioritized findings with explicit evidence links or file references.
- Recommended actions grouped by keep, improve, merge, or retire.
- A short risk note for any recommendation that could remove capabilities.
- Structured output includes
schema_version: 1when requested or when automation will consume the result.
Procedure
- Define scope: single skill, lane, or full inventory.
- Gather evidence from session-collector bundles, session logs, skill metadata, and related references.
- If the session scope is broad or the user references prior attempts, run or consume
~/.agents/session-collectorbefore selecting deep dives; extract only bounded skeleton/error snippets for selected sessions. - Group failures by root cause (coverage gap, instruction drift, routing mismatch, or quality regression).
- Rank recommendations by impact, confidence, and implementation cost.
- Return a concise keep/improve/merge/retire action table with evidence anchors.
What ships with it
14 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 226 B
- assets/skill-refactor.png 7.2 KB
- references/contract.yaml 814 B
- references/evals.yaml 5.6 KB
- references/prompt-injection-expected-context.json 594 B
- references/session-evidence-workflow.md 5.1 KB
- references/task-profile.json 1.2 KB
- scripts/correlate_multi_source_skill_failures.py 349 B runs code
- scripts/scan_codex_sessions.py 331 B runs code
- scripts/test_session_evidence_workflow.py 14 KB runs code
- scripts/test_wrappers.py 338 B runs code
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.
- 12d ago First seen · 91 lines · 44 tokens per session scan A 46ef4a4ea02c
skill-refactor is a skill published in the GitHub repository jscraik/Agent-Skills (8 stars, last pushed 10d ago), licensed Apache-2.0. It adds 44 tokens to every session and 892 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
ad-creative
Plan and produce advertising concepts, copy variants, visual directions, and test matrices for paid campaigns.
humanizer-zh
Revise Chinese text to sound specific, fluent, restrained, and human while preserving facts and author intent.
skill-creator
Design and write concise reusable KunAgent skills with valid triggers, real tools, and testable completion criteria.
daily-brief
Produce a dated, source-linked daily brief with prioritized developments, implications, and watch items.
imf-data
Retrieve and analyze IMF macroeconomic series, forecasts, and reserve-composition data.
scholar-research
Search, screen, synthesize, and cite scholarly literature and author metadata.