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 Jewgah/claude-code-skills --skill loopablegit clone --depth 1 https://github.com/Jewgah/claude-code-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/jewgah/claude-code-skills/loopable)<a href="https://agentmods.dev/skills/jewgah/claude-code-skills/loopable"><img src="https://agentmods.dev/badge/skills/jewgah/claude-code-skills/loopable/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/jewgah/claude-code-skills/loopable"><img src="https://agentmods.dev/badge/skills/jewgah/claude-code-skills/loopable.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 | $0.00053 | $0.00926 |
| Opus 5.5 | $0.00021 | $0.00370 |
| Sonnet 5.5 | $0.00011 | $0.00185 |
| Haiku 4.5 | $0.00005 | $0.00093 |
Grade A, and why
loopable 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Loopable — find what deserves a loop, then build it
You are an automation scout and builder. Input: $ARGUMENTS (focus area, a candidate number like #2, or scan for diagnose-only).
Phase 1: Collect recurrence signals
Run these, skipping any that don't apply:
- Git history:
git log --oneline -200 --pretty='%ad %s' --date=short— cluster commit subjects; repeated verbs/patterns = recurring chores. Ignore one-day bursts; look for rhythm across days/weeks. - Manual scripts:
scripts/,*.sh,*.command, Makefile targets,package.json/composer.jsonscripts run by a human on a rhythm. - Claude usage:
~/.claude/skill-usage.logfiltered to this project + repeated user prompts in~/.claude/projects/<encoded-cwd>/*.jsonl. - Docs & memory: CLAUDE.md / roadmap.md / README chores ("every", "before each", "remember to"); global rules the project violates (e.g. missing roadmap.md).
- Already automated: husky hooks, launchd, cron, GitHub Actions,
.claude/settings.jsonhooks — exclude these; flag near-duplicate existing skills.
Phase 2: Score, rank, pick
Score candidates on frequency (3+ occurrences), determinism, verifiability (machine-checkable success), blast radius. Map each to ONE mechanism: /loop, /schedule, hook, launchd/cron + claude -p, workflow, or plain script (no LLM needed).
Print the ranked table:
| # | Recurring work | Evidence | Mechanism | Trigger + success check | Risk gate |
If $ARGUMENTS is scan, STOP here (report only). Otherwise continue with the top candidate, or the one named #N.
Hard gate: if the chosen candidate automates deploys, pushes, or production-DB changes — STOP and ask for explicit consent before Phase 3.
Phase 3: Plan + review the plan
Write a short implementation plan (files to create/edit, trigger, success check, rollback). Run the /review-plan skill on it and apply its feedback before touching anything.
Phase 4: Implement
Build the automation exactly as planned (hook in settings.json, script, skill, schedule, etc.). Keep it minimal — no features beyond the plan.
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 · 61 lines · 53 tokens per session scan A 19fe1ce129fe
loopable is a skill published in the GitHub repository Jewgah/claude-code-skills (2 stars, last pushed 8d ago), licensed MIT. It adds 53 tokens to every session and 926 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 2026-08-31.
Other skills, from other repositories
triage
A process for reviewing issues and outside pull requests through category and status labels. An issue is a recorded problem or request, while a pull request is a proposed code change for review.
pr
A writing guide for creating pull request descriptions, which explain a proposed code change to reviewers. It uses sections for the summary, evidence, merge risk, and the likely area affected by the change.
code-review
A code-review skill that compares changes from a chosen commit, branch, tag, or merge-base against the repository’s coding standards and the related issue or specification.
improve-codebase-architecture
A skill that scans a codebase for places where restructuring could make future changes and testing easier, then produces an HTML report for selected improvements.
buyer-job-intent-analysis
Recover source-bound buyer jobs, struggling moments, desired progress, forces, workarounds, information acts, journey states, criteria, constraints, roles, locales, and authentic language. Use on approved ICP hypotheses plus customer, search, review, forum, procurement, support, or public-market evidence before…
code-review-checklist
Genera un checklist de revisión de código personalizado para cualquier pull request basado en el lenguaje, tipo de cambio y nivel de riesgo. Úsalo cuando te pidan revisar código, verificar un PR, revisar un pull request o generar un checklist de revisión de código. Produce un checklist enfocado con verificaciones…