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/stackoverworld/primer-ai/adaptive-refactornpx skills add stackoverworld/primer-ai --skill adaptive-refactorgit clone --depth 1 https://github.com/stackoverworld/primer-aiWhat 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 | $0.00000 | $0.00354 |
| Opus 5 | $0.00000 | $0.00177 |
| Sonnet 5 | $0.00000 | $0.00071 |
| Haiku 4.5 | $0.00000 | $0.00035 |
Grade A, and why
adaptive-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 2d 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
Adaptive Refactor Skill
Trigger
Use this skill when a request asks to refactor code while preserving behavior, especially across stack-specific toolchains.
Do Not Trigger
- Net-new feature delivery where behavior-preservation is not the goal.
- Cosmetic-only edits (typos, formatting-only passes, copy changes).
- Pure explanation requests with no code edits.
Workflow
- Start with baseline safety loop:
- establish current behavior and add/confirm invariants
- create a narrow seam for the refactor
- execute smallest safe change
- verify before proceeding
- Apply baseline skill preference:
qa-refactoringas default safe workflow
- Add stack-specific skill(s) when relevant:
- Rust:
rust-refactor-helper - Next.js/React:
vercel-react-best-practices - Node backend:
nodejs-backend-patterns - Swift/iOS:
ios-development - Large Vite reorganizations (optional specialist):
react-vite-expert
- Rust:
- Prefer deterministic verification commands per stack:
- Rust:
cargo fmt,cargo clippy --fix,cargo test - TypeScript + Node backend:
npx tsc --noEmit,npm run test,npm run build - Vite + TypeScript:
npx tsc --noEmit,vitest run,vite build - Swift:
swift format lint .,swift test - Next.js note: use project
eslintscripts instead ofnext lint
- Rust:
- Keep output concise and contract-focused. If contracts change, update docs/ADRs in the same change.
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.
- 2d ago First seen · 32 lines · 0 tokens per session scan A e8abca8f867a
adaptive-refactor is a skill published in the GitHub repository stackoverworld/primer-ai (2 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 354 tokens. 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
orca-emulator-android
Control an Android emulator / device from inside Orca using the orca CLI. Use for listing/booting AVDs, taps, swipes, typing, hardware buttons (incl. Back and Recents), rotation, app install/launch, runtime permissions, the accessibility tree, and logcat — driving a real adb-connected device or emulator.…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
winapp-maui
Package and sign .NET MAUI Windows apps with winapp, resolving the resizetizer manifest dependency. Use when packaging or signing a .NET MAUI Windows app, building a MAUI MSIX or signed unpackaged build in CI, or fixing 'manifest contains unresolved placeholders ($placeholder$)' errors from winapp package.
android-pentest
安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.
react-native-ease-refactor
Scan for Animated/Reanimated code and migrate to EaseView.
app_remix
Create a new Rome app from an App Store source, already installed or identified by a pinned Store version. Copy installed code locally or download and extract a Store bundle without installing the source. Never edit or overwrite an existing source app.