orchestrator-resilience

orchestrator-resilience is a skill for Claude Code from Data-Wise/craft. It costs 81 tokens per session (2,537 once invoked), scanned A, original, MIT.

Reference material for handling failures in a multi-agent orchestrator, a system that coordinates several AI agents. It covers retries, waiting between attempts, circuit breakers, escalation, and execution timelines.

In plain words
What is it for?
Use it to classify failures, retry temporary problems with increasing delays, escalate persistent issues, and show a timeline of what happened.
Why use it?
It helps the orchestrator respond consistently when an agent fails, times out, runs out of resources, or encounters a configuration or code problem.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the craft plugin — 41 skills, 14 commands, 2 agents, 1 MCP server shipped together

Good fit Use it to classify failures, retry temporary problems with increasing delays, escalate persistent issues, and show a timeline of what happened.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/data-wise/craft/orchestrator-resilience
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.

Any agent
npx skills add Data-Wise/craft --skill orchestrator-resilience
Clone the repo
git clone --depth 1 https://github.com/Data-Wise/craft

Made for: Claude Code.

Or install craft, the plugin that ships this one along with the rest of its 41 skills, 14 commands, 2 agents, 1 MCP server.

Wrote 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.

agentmods badge for orchestrator-resilience

README.md
[![agentmods](https://agentmods.dev/badge/skills/data-wise/craft/orchestrator-resilience.svg)](https://agentmods.dev/skills/data-wise/craft/orchestrator-resilience)
Your own site
<a href="https://agentmods.dev/skills/data-wise/craft/orchestrator-resilience"><img src="https://agentmods.dev/badge/skills/data-wise/craft/orchestrator-resilience.svg" alt="Measured on agentmods" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,537 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00081 $0.02537
Opus 5 $0.00041 $0.01269
Sonnet 5 $0.00016 $0.00507
Haiku 4.5 $0.00008 $0.00254

Measured 7d ago against content hash 0589cb08c1a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

orchestrator-resilience 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 7d 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.

skills/orchestrator-resilience/SKILL.md · 281 lines

How it starts

The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestrator Resilience & Timeline Reference

Reference material extracted from agents/orchestrator-v2.md to keep that file's always-loaded system prompt smaller. The orchestrator only needs this content when an agent actually fails, times out, or the user requests a timeline — not on every spawn. See agents/orchestrator-v2.md BEHAVIOR 5 and BEHAVIOR 9 for the pointers into this skill.

Error Categorization

Classify errors to determine appropriate recovery strategy:

Category Examples Recovery Strategy
Transient Network timeout, rate limit, temporary file lock Retry with backoff
Resource Out of memory, disk full, process limit Queue or wait, then retry
Configuration Missing dependency, wrong path, invalid config Auto-fix or escalate
Logical Type error, failed test, syntax error Investigate, then fix or escalate
Permanent File not found, permission denied (after retry) Escalate to user

Retry Logic with Exponential Backoff

## 🔄 RETRY STRATEGY

**Error category**: Transient (network timeout)
**Agent**: code-1
**Attempt**: 2/3
**Previous wait**: 2 seconds
**Current wait**: 4 seconds (exponential backoff)
**Next wait**: 8 seconds (if needed)

### Backoff Schedule
| Attempt | Wait Time | Cumulative |
|---------|-----------|------------|
| 1 | 0s | 0s |
| 2 | 2s | 2s |
| 3 | 4s | 6s |
| 4 | 8s | 14s |
| 5 | 16s (max) | 30s |

**Modified approach**: Using alternate API endpoint
**Timeout**: 30s max per retry

[Retrying with modified approach...]

Timeout Handling

## ⏱️ TIMEOUT MANAGEMENT

**Agent**: test-1
**Task**: Full test suite execution
**Timeout**: 120s (2 minutes)
**Elapsed**: 125s
**Status**: ⚠️ Timeout exceeded

### Timeout Response
1. **Soft timeout** (at 100%): Send interrupt signal
2. **Wait grace period**: 10 seconds
3. **Hard timeout** (at 110%): Force terminate
4. **Fallback**: Run subset of tests (fast tests only)

**Action**: Terminated test-1, spawning test-1-fast with reduced scope

Read the full file on GitHub · 281 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. 7d ago First seen · 281 lines · 81 tokens per session scan A 0589cb08c1a9

Subscribe to this mod's changes

orchestrator-resilience is a skill published in the GitHub repository Data-Wise/craft (4 stars, last pushed 4d ago), licensed MIT. It adds 81 tokens to every session and 2,537 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

architecture-decision-record

ADR templates in the Nygard format with context, decision, consequences, and alternatives. Use when writing ADRs, recording an architectural decision, or evaluating options.

yonatangross/orchestkit · 38 tokens

scope-appropriate-architecture

Right-sizes architecture to project scope, classifying projects into 6 tiers to prevent over-engineering. Use when designing architecture, selecting patterns, or detecting a project tier.

yonatangross/orchestkit · 41 tokens

architecture-review

Conducts a comprehensive multi-perspective architecture review using ALL architecture team members. Use when the user requests "Start architecture review", "Full architecture review", "Review architecture for version X.Y.Z", "Conduct comprehensive review", or when they want assessment from multiple perspectives. Do…

codenamev/ai-software-architect · 80 tokens

architecture-status

Reports on the health and state of architecture documentation (counts of ADRs, reviews, activity levels, documentation gaps). Use when the user asks "What's our architecture status?", "Show architecture documentation", "How many ADRs do we have?", "What decisions are documented?", "Architecture health check", or wants…

codenamev/ai-software-architect · 104 tokens

pragmatic-guard

Enables and configures Pragmatic Guard Mode (YAGNI Enforcement) to prevent over-engineering. Use when the user requests "Enable pragmatic mode", "Turn on YAGNI enforcement", "Activate simplicity guard", "Challenge complexity", or similar phrases.

codenamev/ai-software-architect · 58 tokens

specialist-review

Conducts a focused review from ONE specific specialist's perspective (e.g., Security Specialist, Performance Expert). Use when the user requests "Ask [specialist role] to review [target]", "Get [specialist]'s opinion on [topic]", "Have [role] review [code/component]", or when they want deep expertise in ONE specific…

codenamev/ai-software-architect · 101 tokens