agents-evolution: Skill for Claude Code

.agents/skills/meta/orchestration/recovery/SKILL.md

meta-agent-recovery is a skill for Claude Code, Codex from kissrosecicd-hub/agents-evolution. It costs 67 tokens per session (1,125 once invoked), scanned A, original, MIT.

A recovery guide for coding agents that time out, crash, return incomplete results, or leave dependent agents without needed information. It describes when to retry, skip, use a fallback, or continue with partial results.

In plain words
What is it for?
Use it when an agent hangs, times out, fails to return valid data, crashes, or causes a chain of dependent tasks to fail.
Why use it?
It helps multi-agent work keep moving when one worker fails, while making the failure and its effect visible in the final report.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is kissrosecicd-hub/agents-evolution's own configuration. It tells Claude Code and Codex how to work on agents-evolution itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agents-evolution configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kissrosecicd-hub/agents-evolution. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kissrosecicd-hub/agents-evolution/main/.agents/skills/meta/orchestration/recovery/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/kissrosecicd-hub/agents-evolution

Made for: Claude Code, Codex.

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 meta-agent-recovery

README.md
[![agentmods](https://agentmods.dev/badge/skills/kissrosecicd-hub/agents-evolution/recovery/github.svg)](https://agentmods.dev/skills/kissrosecicd-hub/agents-evolution/recovery)
Your own site
<a href="https://agentmods.dev/skills/kissrosecicd-hub/agents-evolution/recovery"><img src="https://agentmods.dev/badge/skills/kissrosecicd-hub/agents-evolution/recovery/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.

agentmods 80×15 button for meta-agent-recovery

Your own site · 80×15
<a href="https://agentmods.dev/skills/kissrosecicd-hub/agents-evolution/recovery"><img src="https://agentmods.dev/badge/skills/kissrosecicd-hub/agents-evolution/recovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,125 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 $0.00067 $0.01125
Opus 5 $0.00034 $0.00562
Sonnet 5 $0.00013 $0.00225
Haiku 4.5 $0.00007 $0.00112

Measured 10d ago against content hash 0ee7cfd95a35, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

meta-agent-recovery 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 10d 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.

.agents/skills/meta/orchestration/recovery/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Meta: Agent Recovery

Обрабатывает сбои субагентов — таймауты, зависания, каскадные отказы — и обеспечивает graceful degradation.

Типы сбоев

Тип Симптом Причина
Таймаут Агент не отвечает N секунд Задача слишком сложная, модель зависла
JSON парсинг InvalidParameter, function.arguments Ответ слишком длинный, спецсимволы
Каскадный Агент B без данных от агента A Агент A упал, B ожидает его результат
Частичный Агент ответил но не завершил Прервался на середине задачи
Полный Агент вернул ошибку сразу Неподдерживаемый subagent_type

Стратегии восстановления

1. Таймаут → Skip & Continue

Агент не отвечает → ждать 30s → skip → продолжить с остальными →
в отчёте: "X agent skipped (timeout), results from Y agents"

Когда: Агент не критичный для результата.

2. Таймаут → Retry

Агент не отвечает → ждать 30s → повторить с упрощённым промптом →
если снова таймаут → skip

Когда: Агент важный, задача не слишком длинная.

3. Каскадный → Fallback

Агент A упал → агент B не может работать без A →
B тоже skip → main agent делает работу A сам

Когда: Критичный агент (без него весь pipeline ломается).

4. Частичный результат → Использовать

Агент начал но не закончил → взять что есть →
в отчёте: "partial result from X agent, may be incomplete"

Когда: Частичные результаты полезны (нашёл 3 из 5 проблем).

5. Полный сбой → Main agent fallback

Агент вообще не запускается → main agent берёт его роль →
читает SKILL.md → выполняет задачу сам

Когда: Агент недоступен, subagent_type не поддерживается.

Матрица решений

Агент упал Критичен? Действие
code-reviewer Да (основной аудит) Retry → Fallback: main agent делает review
security-auditor Да (безопасность) Retry → Fallback: main agent проверяет секреты
test-architect Нет (можно потом) Skip → пометить «тесты написать позже»
debugger Зависит от бага Если баг критичный → main agent чинит
docs-writer Нет Skip → «документацию добавить позже»
git-doctor Нет Skip → пользователь сделает сам

Read the full file on GitHub · 124 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. 10d ago First seen · 124 lines · 67 tokens per session scan A 0ee7cfd95a35

Subscribe to this mod's changes

meta-agent-recovery is a skill published in the GitHub repository kissrosecicd-hub/agents-evolution (31 stars, last pushed 5mo ago), licensed MIT. It adds 67 tokens to every session and 1,125 once invoked, about $0.0003 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens