New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Loop Recovery

by ntorga in ntorga/agent-starter-kit

Structured recovery and escalation when an agent hits a retry loop.

MITAuto-check passedAI & LLM Engineering

Install Loop Recovery

skills CLI
$ npx skills add ntorga/agent-starter-kit --skill loop-recovery -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ntorga/agent-starter-kit loop-recovery --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ntorga/agent-starter-kit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/loop-recovery .claude/skills/loop-recovery && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
loop-recovery
GitHub stars
146
Token cost
~649 tokens
SKILL.md length
372 words
Files
1
Skills in repo
21
Repo updated
First seen
Licence
MIT

At a glance

Structured recovery and escalation when an agent hits a retry loop.

  • Works in 7 steps: Stop and report. State what was… → Check for oscillation. Before… → Check for drift. If recent actions… → …
  • AI & LLM Engineering work in your project
  • SKILL.md covers Purpose, Procedure and Guardrails
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Loop Recovery is an agent skill from ntorga/agent-starter-kit. Structured recovery and escalation when an agent hits a retry loop.

Its SKILL.md is about 650 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering. The repository describes itself as: The scaffold for your multi-model, personalized Natural Language AI Harness (NLAH) . The licence is MIT.

When your agent uses it

  • AI & LLM Engineering work in your project

Example prompts

  • “/loop-recovery”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Stop and report. State what was attempted and what failed. Do not retry.
  2. Check for oscillation. Before diagnosing, review the last several actions. If the agent has been alternating between two states…
  3. Check for drift. If recent actions touched files unrelated to the stated goal, the agent is flailing. Acknowledge the drift, discard the…
  4. Diagnose. Identify why the approach is not working. The answer must be a root cause, not a symptom — "the API rejects the payload because…
  5. Pivot. Propose a fundamentally different approach. Trivial variations (different whitespace, reordered arguments, minor rewording) do not…
  6. Execute the pivot. Attempt the new approach. If it succeeds, resume normal work. If it fails twice with the same result, proceed to step 7.
  7. Abandon and hand off. Return a handoff explaining

What it can do on your machine

Read from SKILL.md and the folder at commit 851e942. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Loop Recovery loads about 649 tokens when it runs. Until then it costs about 20 tokens; SKILL.md has 372 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~20
When it runs · the whole SKILL.md, loaded when a task matches
~649

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ntorga/agent-starter-kit at commit 851e942, republished under its MIT licence (© ntorga). 372 words, ~649 tokens.

Download SKILL.mdSave it as .claude/skills/loop-recovery/SKILL.md (or your agent's skills folder).
name
loop-recovery
description
Structured recovery and escalation when an agent hits a retry loop.
usedBy
all
version
0.0.3
lastUpdated
2026-09-12

Purpose

When an agent has repeated the same failing action three times, it needs a concrete recovery procedure — not just the instruction to "reassess." This skill defines the recovery steps, the escalation path when the second approach also fails, and the detection patterns that catch loops before they waste effort.

Procedure

  1. Stop and report. State what was attempted and what failed. Do not retry.

  2. Check for oscillation. Before diagnosing, review the last several actions. If the agent has been alternating between two states — modifying file A, then file B, then file A again, or toggling between two error messages — the loop is structural, not incidental. Skip straight to step 5 on second detection.

  3. Check for drift. If recent actions touched files unrelated to the stated goal, the agent is flailing. Acknowledge the drift, discard the unrelated changes, and refocus on the original objective before diagnosing.

  4. Diagnose. Identify why the approach is not working. The answer must be a root cause, not a symptom — "the API rejects the payload because field X is required" is a diagnosis; "it returns 400" is a symptom.

  5. Pivot. Propose a fundamentally different approach. Trivial variations (different whitespace, reordered arguments, minor rewording) do not count as a different approach. If no alternative exists, skip to step 7.

  6. Execute the pivot. Attempt the new approach. If it succeeds, resume normal work. If it fails twice with the same result, proceed to step 7.

  7. Abandon and hand off. Return a handoff explaining:

    • The original approach and why it failed.
    • The alternative approach and why it also failed (or why no alternative existed).
    • What is needed to unblock (different tooling, human intervention, missing information).
Show full SKILL.md (90 more words)Show less

Guardrails

  • Never attempt a third approach. Two failed approaches show the problem needs human judgment or context the agent lacks.
  • Never retry with debug commands, additional logging, or exploratory reads unless the new information would change the approach — not merely confirm the same failure.
  • Never continue after detecting oscillation twice. An A→B→A→B cycle means the two approaches are undoing each other — a third attempt will repeat the pattern.
  • Never treat drift (touching unrelated files) as progress. If the last action modified files outside the task scope, revert it before proceeding.

© ntorga, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/loop-recovery of ntorga/agent-starter-kit.

Open the folder on GitHubat commit 851e942

Compare with similar skills

Loop Recovery next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Loop Recovery compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Loop Recovery this skillntorga/agent-starter-kit146—~649Automated safety check: PassMIT
Agent BuildershareAI-lab/learn-claude-code78k6 repos~1.2kAutomated safety check: PassMIT
Add Uint Supportpytorch/pytorch104k2 repos~2.3kAutomated safety check: PassCustom licence
Peft Fine TuningOrchestra-Research/AI-Research-SKILLs13k9 repos~3.1kAutomated safety check: PassMIT
Segment Anything Model GuideOrchestra-Research/AI-Research-SKILLs13k9 repos~3.3kAutomated safety check: PassMIT
1passwordtrpc-group/trpc-agent-go1.8k15 repos~656Automated safety check: PassApache-2.0

Similar skills

  • Agent Builder

    shareAI-lab/learn-claude-code

    Design and build AI agents for any domain. An agent skill from shareAI-lab/learn-claude-code.

    78k GitHub starsUsed in 6 repos~1.2k tokens
    AI & LLM EngineeringAuto-check passed

  • Add Uint Support

    pytorch/pytorch

    Add unsigned integer (uint) type support to PyTorch operators by updating ATDISPATCH macros.

    104k GitHub starsUsed in 2 repos~2.3k tokens
    AI & LLM EngineeringAuto-check passed

  • Peft Fine Tuning

    Orchestra-Research/AI-Research-SKILLs

    Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods.

    13k GitHub starsUsed in 9 repos~3.1k tokens
    AI & LLM EngineeringAuto-check passed

  • Segment Anything Model Guide

    Orchestra-Research/AI-Research-SKILLs

    Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.

    13k GitHub starsUsed in 9 repos~3.3k tokens
    AI & LLM EngineeringAuto-check passed

  • 1password

    trpc-group/trpc-agent-go

    Set up and use 1Password CLI (op). An agent skill from trpc-group/trpc-agent-go.

    1.8k GitHub starsUsed in 15 repos~656 tokens
    AI & LLM EngineeringAuto-check passed

  • Chroma Vector Database

    Orchestra-Research/AI-Research-SKILLs

    Shows how to store documents and embeddings in Chroma, query them by similarity with metadata filters, and persist them to disk for RAG and semantic search projects.

    13k GitHub starsUsed in 8 repos~2.3k tokens
    AI & LLM EngineeringAuto-check passed

More from ntorga/agent-starter-kit

All 21 skills in this repo

  • Agent Decision

    ntorga/agent-starter-kit

    Deterministic self-evaluation rubric for decision escalations — scored every run using the FRAME framework.

    146 GitHub stars~1.7k tokensUpdated 25 days ago
    Auto-check passed

  • Agent Memory

    ntorga/agent-starter-kit

    Long-term and session memory across sessions. An agent skill from ntorga/agent-starter-kit.

    146 GitHub stars~2.7k tokensUpdated 25 days ago
    Auto-check passed

  • Architect Design Tree

    ntorga/agent-starter-kit

    Builds the design tree for the grill — decisions mapped as nodes with dependencies, recommendations, and impact, pruned by path.

    146 GitHub stars~1.2k tokensUpdated 25 days ago
    Auto-check passed

  • Architect Impl Grounding

    ntorga/agent-starter-kit

    Grounds the grill's settled decisions in the codebase — annotates impl.md with file paths, signatures, reference files, test specs, and LOC; re-grounds the next epic after each landing.

    146 GitHub stars~944 tokensUpdated 25 days ago
    Auto-check passed

  • Boot

    ntorga/agent-starter-kit

    Session startup — gitignore, auto-update, memory, rules, context, CLI config, and greet.

    146 GitHub stars~937 tokensUpdated 25 days ago
    Auto-check passed

  • Browser Inspect

    ntorga/agent-starter-kit

    Browser inspection and interaction for verifying rendered web UI during development.

    146 GitHub stars~2k tokensUpdated 25 days ago
    Auto-check passed

Categories

Questions about Loop Recovery

What does Loop Recovery do?

Structured recovery and escalation when an agent hits a retry loop. Loop Recovery is an agent skill from ntorga/agent-starter-kit. Structured recovery and escalation when an agent hits a retry loop.

When should I use Loop Recovery?

Loop Recovery fits situations like: AI & LLM Engineering work in your project.

How do I install Loop Recovery in Claude Code?

Run `npx skills add ntorga/agent-starter-kit --skill loop-recovery -a claude-code`. Or copy the skill folder (skills/loop-recovery in ntorga/agent-starter-kit) into .claude/skills/loop-recovery in your project. Claude Code loads it when a task matches its description.

How do I install Loop Recovery in Codex?

Run `npx skills add ntorga/agent-starter-kit --skill loop-recovery -a codex`. Or copy the skill folder (skills/loop-recovery in ntorga/agent-starter-kit) into .agents/skills/loop-recovery in your project. Codex loads it when a task matches its description.

Can I use Loop Recovery in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ntorga/agent-starter-kit --skill loop-recovery -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/loop-recovery, .gemini/skills/loop-recovery, .github/skills/loop-recovery and .opencode/skills/loop-recovery in your project.

What does Loop Recovery need to run?

SKILL.md names no scripts, command-line tools or credentials: Loop Recovery is instructions for the agent only.

Does Loop Recovery access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Loop Recovery safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Loop Recovery use?

Loop Recovery is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Loop Recovery use?

About 649 tokens (SKILL.md is roughly 2.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Loop Recovery?

Skills that share tags, products or a category with Loop Recovery: Agent Builder (shareAI-lab/learn-claude-code, 78k stars), Add Uint Support (pytorch/pytorch, 104k stars), Peft Fine Tuning (Orchestra-Research/AI-Research-SKILLs, 13k stars) and Segment Anything Model Guide (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Loop Recovery?

ntorga (a GitHub user) maintains it in ntorga/agent-starter-kit, which has 146 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on September 12, 2026.

Source: ntorga/agent-starter-kit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.