error-recovery-patterns

A set of patterns for handling errors in gh-aw, GitHub’s command-line tool for creating AI-powered workflows from Markdown files. It covers retries, recovery steps, circuit breakers, and debugging logs.

In plain words
What is it for?
Use it to add retry limits and delays, recover from installation or API problems, prevent repeated failure loops, classify errors, and record recovery attempts for debugging.
Why use it?
It helps workflows recover from temporary network, installation, dependency, or API failures without retrying forever. It also helps distinguish errors worth retrying from errors that should stop immediately.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/github/gh-aw/error-recovery-patterns
Any agent
npx skills add github/gh-aw --skill error-recovery-patterns
Clone the repo
git clone --depth 1 https://github.com/github/gh-aw

Made for: Claude Code, Codex.

Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 674 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00020 $0.00674
Opus 5 $0.00010 $0.00337
Sonnet 5 $0.00004 $0.00135
Haiku 4.5 $0.00002 $0.00067

Measured yesterday against content hash dee85b04fab2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

error-recovery-patterns 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 yesterday.

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.

.github/skills/error-recovery-patterns/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Error Recovery Patterns Skill

Use this skill for error handling, recovery strategies, and debugging in gh-aw.

Purpose

Implement robust recovery patterns to:

  • Reduce retry loops in agent sessions (target: <10% vs current 23%)
  • Implement circuit breakers to prevent infinite retry loops
  • Add proactive recovery for installation, dependency, and API failures
  • Improve debug logging for recovery attempts

When to Use This Skill

Use this skill when:

  • Implementing retry logic for network operations, installations, or API calls
  • Debugging retry loop issues in workflows or agent sessions
  • Adding error recovery patterns to new or existing code
  • Understanding transient vs non-transient error classification
  • Implementing circuit breakers or exponential backoff
  • Adding debug logging for recovery attempts

Key Concepts Covered

1. Circuit Breaker Pattern

  • Maximum retry limits (standard: 3 attempts)
  • Exponential backoff strategies
  • Fail-fast on non-transient errors
  • Implementation in JavaScript, Shell, and Go

2. Installation Failure Recovery

  • NPM installation with cache clearing and registry fallbacks
  • Python pip installation with mirror alternatives
  • Docker image pull with retry and rate limit handling
  • Copilot CLI installation with network retry

3. API Timeout and Rate Limit Handling

  • GitHub API rate limit detection and backoff
  • Transient error detection patterns
  • Custom retry configuration for different APIs
  • Rate limit-specific retry strategies

4. Debug Logging for Recovery

  • Logger package usage for retry attempts
  • Category naming conventions (pkg:filename)
  • DEBUG environment variable patterns
  • Zero-overhead logging when disabled

5. Error Categorization

  • Transient vs non-transient errors
  • Network errors, timeout patterns
  • HTTP error codes (502, 503, 504)
  • GitHub-specific errors (rate limits, abuse detection)

Anti-Patterns to Avoid

This skill explicitly covers anti-patterns to avoid:

  • ❌ Infinite retry loops without maximum limits
  • ❌ Retrying validation errors that won't self-correct
  • ❌ No backoff delay between attempts
  • ❌ Silent retries without logging
  • ❌ Retrying non-transient errors

Read the full file on GitHub · 97 lines

Changes

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.

  1. yesterday First seen · 97 lines · 20 tokens per session scan A dee85b04fab2

Subscribe to this mod's changes

error-recovery-patterns is a skill published in the GitHub repository github/gh-aw (5,050 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 674 once invoked, about $0.0001 per session on Opus 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.

Related

Other skills, from other repositories

c-github

Interact with GitHub using the gh CLI and jq. Manage PRs, issues, repositories, and Actions workflows. Make raw API calls with gh api for anything not covered by built-in commands.

daxaur/openpaw · 48 tokens

watch-pr

Watch a GitHub pull request for CI status, reviews, comments, merge conflicts, and terminal states using the gh-watch extension. Use when the user wants to monitor a PR, wait for CI, or track PR progress.

justincampbell/gh-watch · 48 tokens

watch-tag

Watch a GitHub repository for new tags using the gh-watch extension. Use when the user wants to be notified when a tag is created, when a release is cut, or when a tag that includes a specific commit appears (e.g. "tell me when my merge ships in a release").

justincampbell/gh-watch · 62 tokens

watch-branch

Watch a GitHub branch for new commits using the gh-watch extension. Use when the user wants to be notified when new commits are pushed to a branch, monitor main for merges, or track branch activity.

justincampbell/gh-watch · 45 tokens

watch-commit

Watch a GitHub commit for CI status changes using the gh-watch extension. Use when the user wants to monitor a commit's CI checks, wait for a build to finish, or track CI progress on a specific SHA.

justincampbell/gh-watch · 48 tokens

update-architecture-docs

Generate or update the architecture documentation in docs/content/architecture/. Use on "update architecture docs", "generate architecture documentation", "regenerate architecture docs", or after any structural change to the codebase.

AlexSkrypnyk/scaffold · 46 tokens