error-recovery

error-recovery is a skill for Claude Code from marcusgoll/Spec-Flow. It costs 34 tokens per session (1,932 once invoked), scanned C, original, MIT.

A workflow recovery helper that classifies failures and decides whether they can be fixed automatically or need a person.

In plain words
What is it for?
It helps handle failures during feature and sprint implementation and quality gates.
Why use it?
It prevents unsafe retries for serious failures such as broken CI, failed security scans, or failed deployments.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit It helps handle failures during feature and sprint implementation and quality gates.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/marcusgoll/spec-flow/error-recovery
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 marcusgoll/Spec-Flow --skill error-recovery
Clone the repo
git clone --depth 1 https://github.com/marcusgoll/Spec-Flow

Made for: Claude Code.

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 error-recovery

README.md
[![agentmods](https://agentmods.dev/badge/skills/marcusgoll/spec-flow/error-recovery.svg)](https://agentmods.dev/skills/marcusgoll/spec-flow/error-recovery)
Your own site
<a href="https://agentmods.dev/skills/marcusgoll/spec-flow/error-recovery"><img src="https://agentmods.dev/badge/skills/marcusgoll/spec-flow/error-recovery.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,932 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00034 $0.01932
Opus 5 $0.00017 $0.00966
Sonnet 5 $0.00007 $0.00386
Haiku 4.5 $0.00003 $0.00193

Measured 4d ago against content hash 5f3238998b6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade C, and why

error-recovery scanned grade C with 1 finding 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 4d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf .next .cache coverage node_modules/.cache dist build
.claude/skills/error-recovery/SKILL.md · 276 lines

How it starts

The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use this skill when:

  • Sprint fails during /implement-epic
  • Feature fails during /implement
  • Quality gate blocks deployment
  • Any workflow phase returns FAILED status

<quick_start> When a workflow component fails:

  1. Classify the failure using the decision tree below
  2. If fixable: Execute auto-fix strategies (max 3 attempts)
  3. If critical: Stop immediately, report to user
  4. If unknown: Treat as critical (safe default)

Classification determines whether workflow can auto-recover or requires user intervention. </quick_start>

<failure_classification>

Critical Blockers (MUST STOP)

These failures require manual intervention - never auto-retry:

Failure Type Detection Why Critical
CI Pipeline ci_pipeline_failed: true in state.yaml GitHub Actions/GitLab CI failed - indicates code issue
Security Scan security_scan_failed: true High/Critical CVEs found - security risk
Deployment deployment_failed: true Production/staging crashed - user-facing impact
Contract Violation contract_violations > 0 API contract broken - breaks consumers

Action: Stop workflow, report error details, require /continue after manual fix.

Fixable Issues (CAN AUTO-RETRY)

These failures often resolve with automated fixes:

Failure Type Detection Auto-Fix Strategies
Test Failures tests_failed: true (no CI failure) re-run-tests, check-dependencies
Build Failures build_failed: true clear-cache, reinstall-deps, rebuild
Dependency Issues dependencies_failed: true clean-install, clear-lockfile
Infrastructure infrastructure_issues: true restart-services, check-ports
Type Errors type_check_failed: true (manual fix usually required)

Action: Attempt auto-fix strategies (max 3 attempts), then escalate if all fail.

Read the full file on GitHub · 276 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. 4d ago First seen · 276 lines · 34 tokens per session scan C 5f3238998b6f

Subscribe to this mod's changes

error-recovery is a skill published in the GitHub repository marcusgoll/Spec-Flow (92 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 1,932 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

qa

Interactive QA session where user reports bugs or issues conversationally, and the agent files GitHub issues. Explores the codebase in the background for context and domain language. Use when user wants to report bugs, do QA, file issues conversationally, or mentions "QA session".

mhrsdev/AI-Agent-Skills-Library · 58 tokens

bug-triage

Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic trends, and produce a triage report. Run at sprint start or when the bug count grows enough to need re-prioritization.

Donchitos/Claude-Code-Game-Studios · 59 tokens

clash-resolution-analyzer

Analyze BIM clash detection results and suggest resolutions. Prioritize clashes, identify patterns, assign responsibility, and track resolution status.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction · 30 tokens

bugherd-automation

Automate Bugherd tasks via Rube MCP (Composio). Always search tools first for current schemas.

ComposioHQ/awesome-claude-skills · 29 tokens

worker

Team worker protocol (ACK, mailbox, task lifecycle) for tmux-based OMX teams.

IAPro-Community/Orquestrador-Maestro · 19 tokens

incident-learning

Convert operational incident and near-miss evidence into durable product, engineering, test, evaluation, and governance improvements with verified closure. Separate observed facts from causal hypotheses and unresolved uncertainty; map follow-up work across code, tests, skills, operations, product, and governance…

magnus919/agent-skills · 98 tokens