running-agent-loops SKILL.md skillA
This file is byte-identical to the first copy the registry indexed. Same content hash, so the same checks give both the same grade.
running-agent-loops from cristhianzl/claude-skills-czl is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add cristhianzl/claude-skills-czl/running-agent-loops@git:20261103.b450fa3Pins git:20261103.b450fa3 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- cristhianzl/claude-skills-czl
- Path
configs/langflow/skills/running-agent-loops/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261103.b450fa3, committed Nov 3, 2026
- First version recorded
- Jun 25, 2026
- Size
- 4,526 bytes
- Repository stars
- 5
- License
- MIT
Run a multi-step or unattended agent loop safely — sequential pipelines, implement→review→fix (PR) loops, parallel fan-out, and RFC→DAG orchestration. Use when the user wants to "loop", "run autonomously", "iterate until it's done", chain `claude -p` calls, fan out parallel agents on a spec, or set up an implement→verify→commit cycle. Covers the cross-iteration context bridge and the de-sloppify pass. Not for a single one-shot task.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Running agent loops Patterns for driving work across **many steps or iterations** — possibly unattended — without the run drifting, looping, or shipping slop. The core trade is **isolation vs. continuity**: a fresh context per step avoids bleed, but you must deliberately carry forward what matters. ## Read first (always) List `learnings/` and read anything relevant. Project-specific loop conventions, budgets, and stop signals live there and override this file. ## Principles (apply to every loop) - **Fresh context per step beats one long context.** Each `claude -p` / subagent call starts clean — no bleed, no drift. The cost: it forgets. Bridge it deliberately (below). - **The reviewer is never the author.** Put review/verify in a separate step/context so it isn't anchored to the implementation. - **Two focused passes beat one constrained pass.** Don't pile negative instructions onto the implementer — add a separate **de-sloppify** pass (below). Quality from constraints decays; quality from a dedicated cleanup step doesn't. - **Every loop has an explicit stop condition.** Bound it by max-runs, max-cost, max-duration, or a completion signal — never "until it feels done". …
Read the whole file at its exact version.
How to install
mdr add cristhianzl/claude-skills-czl/running-agent-loops@sha256:f5d9f879c8f83f1dThe line at the top of this page pins the label git:20261103.b450fa3, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_rsxkamnbxib2bwcj)
6 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Jun 25, 2026 and Nov 3, 2026, about one every 131 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261103.b450fa3 latest | 2026-11-03 | b450fa3 | 4,526 B | A | view · diff |
| git:20260625.6520aec | 2026-06-25 | 6520aec | 4,221 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4526 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
cristhianzl/claude-skills-czl · 5 stars · license MIT · pushed 2026-11-03 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_rsxkamnbxib2bwcj GET https://markdownregistry.com/api/v1/resolve?ref=cristhianzl/claude-skills-czl/running-agent-loops GET https://markdownregistry.com/api/v1/blob/f5d9f879c8f83f1dbd4772e1abd42071092a904d3689ba926105bb8589bf6d67
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from cristhianzl/claude-skills-czl
Every file in cristhianzl/claude-skills-czl