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 ai-driven-dev/framework --skill 07-refactorgit clone --depth 1 https://github.com/ai-driven-dev/frameworkWrote 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/ai-driven-dev/framework/07-refactor)<a href="https://agentmods.dev/skills/ai-driven-dev/framework/07-refactor"><img src="https://agentmods.dev/badge/skills/ai-driven-dev/framework/07-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/ai-driven-dev/framework/07-refactor"><img src="https://agentmods.dev/badge/skills/ai-driven-dev/framework/07-refactor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00057 | $0.00535 |
| Opus 5.5 | $0.00023 | $0.00214 |
| Sonnet 5.5 | $0.00011 | $0.00107 |
| Haiku 4.5 | $0.00006 | $0.00053 |
Grade A, and why
07-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 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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: refactor
The act-side of code improvement: it changes code to make it better. Behavior-preserving for cleanup, performance, and architecture; security may change behavior on purpose to close a hole.
Actions
| # | Action | Axis | Lens |
|---|---|---|---|
| 01 | performance |
performance | N+1, hot paths, batching, memoization, unnecessary I/O |
| 02 | security |
security | OWASP, input validation, authz, secrets: harden and fix |
| 03 | cleanup |
code-quality | clean code: rename, extract, DRY, dead code, complexity |
| 04 | architecture |
architecture | extract layers, fix coupling, enforce boundaries |
Run the one axis named, or offer all applicable when the request is unscoped.
Before running an action, read its file in actions/, not only the table or assets.
Transversal rules
- Scope: run the one named axis, or for an unscoped request ask once "all applicable axes, or one?" before running. A request to delete or remove code runs
cleanupdirectly, with no axis question. Never silently default to one axis. - Behavior-preserving for cleanup, performance, and architecture: public inputs and outputs stay identical, verified by tests, type checks, or a side-by-side run. Security may alter behavior to close a vulnerability, and must call that out explicitly.
- Audit-fed, optional: when the caller pushes an audit report (a path under
aidd_docs/tasks/audits/or pasted findings), take its findings for this axis as the fix list and skip the scan. The bridge is the report artifact; this skill never loads or calls another skill. The auditcode-qualitypillar feeds thecleanupaxis; the other axes map by name. - Severity uses the shared 3-level scale: 🔴 critical, 🟡 major, 🟢 minor.
- Stay inside the axis: dependency upgrades and UI redesign are out of scope. Add tests only as a regression for a security fix, never otherwise.
What ships with it
4 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 Changed 982f3a78293b
- 1mo ago First seen · 30 lines · 57 tokens per session scan A 9450d45cc7aa
07-refactor is a skill published in the GitHub repository ai-driven-dev/framework (523 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 535 once invoked, about $0.0002 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
error-recovery
A guide to detecting and recovering from failures in long-running AI agents. It covers API outages, bad tool calls, broken conversation state, stalled streams, repeated loops, retries, fallback models, and circuit breakers that stop repeated failure.
code-search
Search a codebase efficiently with ripgrep regular expressions, file globs, and git history search. Use to locate symbols, usages, and definitions instead of reading whole files.
doctor
Diagnose and repair your TinyFish setup — MCP registration, auth, and connectivity. Runs the TinyFish CLI's own doctor for the config checks, then does the one thing the CLI cannot — proving this harness can actually reach TinyFish. Run when TinyFish tools fail, return auth errors, or after an install that did not…
feedback
File structured feedback about TinyFish — bug reports, confusing setup steps, missing features, or a doctor diagnostic report. Creates a GitHub issue on tinyfish-io/tinyfish-cookbook with the user's approval; nothing is sent without an explicit preview.
ci-troubleshoot
Diagnose failed GitHub Actions runs for pi-agent-dashboard: the 11-file workflow taxonomy, affected-test selection, the release pipeline, known failure modes, and how to read gh run logs and retrigger jobs. Use when a CI run is red, a release is stuck, a workflow won't dispatch, or you need to know which workflow does…
performance-optimization
Measure-first performance work. Use on triggers like "it's slow", "profile this", "optimize perf", "fix the bottleneck", "improve load time / Core Web Vitals", or when a measured regression needs fixing. Enforces measure-before-optimize. Fills a perf gap not covered by existing project skills. Not a build/ship…