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 frankxai/claude-skills-library --skill loop-runnergit clone --depth 1 https://github.com/frankxai/claude-skills-libraryWrote 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/frankxai/claude-skills-library/loop-runner)<a href="https://agentmods.dev/skills/frankxai/claude-skills-library/loop-runner"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/loop-runner/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/frankxai/claude-skills-library/loop-runner"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/loop-runner.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 | $0.00104 | $0.01971 |
| Opus 5.5 | $0.00042 | $0.00788 |
| Sonnet 5.5 | $0.00021 | $0.00394 |
| Haiku 4.5 | $0.00010 | $0.00197 |
Grade A, and why
loop-runner 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Loop Runner
You are one iteration of a durable loop. You start cold, you finish clean, and everything you learn goes into files — the next iteration (possibly a different agent, possibly you tomorrow) knows only what the loop directory says. Run exactly one unit; resist finishing "just one more".
The iteration protocol
Execute in order. Do not skip, reorder, or batch steps.
0 · Load
Read, in this order: .loop/<name>/LOOP.md (the whole charter), .loop/<name>/signs.md
(every line is a binding rule earned from a past failure — treat them like
Guardrails), .loop/<name>/state.json, the last 3 entries of
.loop/<name>/journal.md, and .loop/<name>/backlog.md if the archetype uses one.
Do not read the full journal — old entries are archive, not context.
1 · Gate
Refuse to run (exit with one journal line explaining why) if ANY of:
.loop/STOPor.loop/<name>/STOPexists — the operator's kill switch. Never delete a STOP file.statusispaused,stalled,blocked,done, orretired— only an operator or the orchestrator changes those.iteration >= budget.max_iterations.- Done-when already passes → set
status: done, journal it, report, stop. - The working tree is dirty with changes this loop didn't journal → set
status: blocked, escalate per charter (H4 debris — a prior iteration died; a human or the orchestrator must adjudicate, not you).
Then check .loop/<name>/STEER.md. If present, it is live operator steering:
incorporate it into this iteration's choices, quote it in the journal entry, then
delete the file. Steering outranks the journal's Next: hint but never overrides
Guardrails or promotion mode.
2 · Pick
Select the single unit per the charter's Iteration contract (top eligible backlog
item; next failing test; the current blocker for a babysitter; …). If the last
journal entry's Next: names a unit, prefer it unless it's now ineligible. If the
same unit appears in the last 2 entries with ❌, you MUST take a different approach
or escalate — never re-run a failed approach verbatim.
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 · 142 lines · 104 tokens per session scan A 967774c1807c
loop-runner is a skill published in the GitHub repository frankxai/claude-skills-library (47 stars, last pushed today), licensed MIT. It adds 104 tokens to every session and 1,971 once invoked, about $0.0004 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
token-saver
Token optimization guide for Claude Code. This skill should be used when the user wants to reduce API costs, learn model routing strategies, or understand how to use free/cheaper tools (Ollama, Haiku) instead of burning expensive Claude tokens on routine tasks. Triggers on: save tokens, reduce costs, token tips, cheap…
wayfinder
A planning method that maps a large, uncertain project into linked decision tickets in a repository's issue tracker. An issue tracker is a system for recording and organizing project work.
scaffold-exercises
A directory scaffold for course exercises, with sections, exercise folders, and optional problem, solution, or explanation versions. It creates the required Markdown files and checks the result with the repository's linter.
domain-modeling
A practice for building and maintaining a project’s domain model: the shared terms, concrete scenarios, and recorded architecture decisions that describe what the software is about.
migrate-to-shoehorn
A testing guide for Shoehorn, a TypeScript library that lets tests provide only the fields they need from a larger data type.
ask-matt
A skill router that helps choose the right workflow or skill for the current task. It maps work from an initial idea through building and shipping, with separate paths for research, prototypes, and multi-session projects.