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 lexler/skill-factory --skill hotspotsgit clone --depth 1 https://github.com/lexler/skill-factoryWrote 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/lexler/skill-factory/hotspots)<a href="https://agentmods.dev/skills/lexler/skill-factory/hotspots"><img src="https://agentmods.dev/badge/skills/lexler/skill-factory/hotspots/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/lexler/skill-factory/hotspots"><img src="https://agentmods.dev/badge/skills/lexler/skill-factory/hotspots.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 | $0.01115 |
| Opus 5.5 | $0.00023 | $0.00446 |
| Sonnet 5.5 | $0.00011 | $0.00223 |
| Haiku 4.5 | $0.00006 | $0.00112 |
Grade A, and why
hotspots 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
STARTER_CHARACTER = 🔥
Hotspot analysis ranks files by change frequency × complexity. Code that is both complicated and changed often is where refactoring pays; complicated but stable code is not — "if it never changes, it's not costing us money." The scripts compute every number deterministically; your job is scoping, validation, and interpretation. A hotspot is a pointer to where to look, never a diagnosis.
If the user wants to check whether a past refactoring paid off and hotspots/data/mine.json exists in the repo, jump to VERIFY. Otherwise run the steps in order.
1. SCOPE
Decide and record:
- Window: default 12 months; use "since last major release" if the user names one. Under ~6 months of history, warn that rankings are unreliable.
- Target: repo root, or the subtree the user cares about in a monorepo.
- Extra excludes: skim the tree for generated/vendored content the defaults miss (see default list in
scripts/mine.py). Keep test files in — a test file as top hotspot is a real and common finding. - History quality: if most commits are PR squashes, note that coupling signal is weakened.
Done when window, target, and extra excludes are chosen and any history caveats are noted for the report header.
2. MINE
uv run ${CLAUDE_SKILL_DIR}/scripts/mine.py <repo> --months <N> [--exclude PATTERN]... --out hotspots/data/mine.json
uv run ${CLAUDE_SKILL_DIR}/scripts/coupling.py <repo> --months <N> [--exclude PATTERN]... --out hotspots/data/coupling.json
Pass the same --months and --exclude flags to both. If summary.warnings reports too few commits or nothing ranked, widen the window or lower --min-revs and re-run.
Done when both JSON files exist and files_ranked > 0.
3. VALIDATE
Take the top ~10 files by score from mine.json. Read each one and give a verdict — confirmed hotspot, or discarded with the false-positive class it belongs to (catalog in references/interpretation.md). When discards free up slots, pull in the next candidates so ~10 get verdicts.
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.
- 1mo ago First seen · 70 lines · 57 tokens per session scan A c2b036cd9899
hotspots is a skill published in the GitHub repository lexler/skill-factory (239 stars, last pushed 16d ago), licensed Apache-2.0. It adds 57 tokens to every session and 1,115 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 2026-08-30.
Other skills, from other repositories
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
github-contributor
A step-by-step guide for contributing code, tests, documentation, or build changes to open-source projects you do not maintain. It explains how to prepare a pull request that follows the project’s rules and is easier for maintainers to review.
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…