Error Recovery

Error Recovery is a skill for Claude Code from ralfyishere/rules-with-receipts. It costs 112 tokens per session (1,603 once invoked), scanned A, original, MIT.

A recovery procedure for when attempts to fix a coding task make the project’s state unclear or worse. It helps decide whether to return to a known state or continue with a deliberate fix.

In plain words
What is it for?
Use it after two failed attempts at the same problem, after changes break working tests, or when debug code and partial reversals are mixed together.
Why use it?
It prevents repeated patches and experiments from compounding the original problem. This keeps debugging work understandable after failed fixes or newly broken tests.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it after two failed attempts at the same problem, after changes break working tests, or when debug code and partial reversals are mixed together.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ralfyishere/rules-with-receipts/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 ralfyishere/rules-with-receipts --skill error-recovery
Clone the repo
git clone --depth 1 https://github.com/ralfyishere/rules-with-receipts

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/ralfyishere/rules-with-receipts/error-recovery/github.svg)](https://agentmods.dev/skills/ralfyishere/rules-with-receipts/error-recovery)
Your own site
<a href="https://agentmods.dev/skills/ralfyishere/rules-with-receipts/error-recovery"><img src="https://agentmods.dev/badge/skills/ralfyishere/rules-with-receipts/error-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 Error Recovery

Your own site · 80×15
<a href="https://agentmods.dev/skills/ralfyishere/rules-with-receipts/error-recovery"><img src="https://agentmods.dev/badge/skills/ralfyishere/rules-with-receipts/error-recovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,603 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 $0.00112 $0.01603
Opus 5 $0.00056 $0.00801
Sonnet 5 $0.00022 $0.00321
Haiku 4.5 $0.00011 $0.00160

Measured 10d ago against content hash d720b31dcb78, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

Error 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.

.claude/skills/error-recovery/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Error Recovery

Purpose

The most expensive failures aren't the first error — they're the recovery attempts that compound it: patches stacked on unverified patches, experiments left half-applied, a working state destroyed by attempts to improve it. This skill is the circuit breaker: recognize the spiral early, stabilize to a known state, and choose revert or fix forward deliberately instead of by momentum. It governs your own work going wrong mid-task — debugging-playbook diagnoses defects in the artifact; this skill manages you when the fixing itself is failing.

When to use this skill

  • The two-strike rule fires: two consecutive attempts at the same problem have failed. Stop; do not try "one more thing."
  • Your changes broke something that was working (newly red tests, new errors elsewhere).
  • You can't state precisely what's currently applied: experiments, debug prints, half-reverted edits are mixed together.
  • Any moment where the honest status is "worse than when I started."

When NOT to use this skill

  • First failure of a first attempt — that's normal iteration; go to debugging-playbook.
  • Expected failures during exploratory work you've isolated (a scratch branch, a sandbox). Spirals only count in state that matters.

Operating procedure

1 — Stop. The urge to immediately try the next patch is the spiral's engine. No edits for the duration of steps 2–4.

2 — Establish where you are. Diff the current state against the last known-good state (git diff/git status, document version history, the original file). List: what changed, what's broken now that wasn't, which changes were deliberate vs. debris (debug prints, commented-out blocks, abandoned experiments).

3 — Preserve the evidence. Before any revert, save what the failed attempts taught: the diff of each attempt, the exact errors, what you predicted vs. what happened — to a scratch file or note. Reverting without capturing this deletes the learning along with the mess.

Read the full file on GitHub · 77 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 · 77 lines · 0 tokens per session scan A d720b31dcb78

Subscribe to this mod's changes

Error Recovery is a skill published in the GitHub repository ralfyishere/rules-with-receipts (2 stars, last pushed 2mo ago), licensed MIT. It adds 112 tokens to every session and 1,603 once invoked, about $0.0006 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

code-review

Reviews code for bugs, security issues, and best practices.

promptfoo/promptfoo · 11 tokens

error-translator

A Chinese-language assistant that translates English programming errors and explains what they mean. It covers common errors from languages and frameworks including Python, JavaScript, TypeScript, Java, and others.

laolaoshiren/claude-code-skills-zh · 28 tokens

eslint-fix

A project-aware assistant for finding and fixing ESLint errors, warnings, and configuration compatibility problems. ESLint is a tool that checks JavaScript and TypeScript code for style and common mistakes.

laolaoshiren/claude-code-skills-zh · 79 tokens

perf-profiler

A performance investigation guide that uses repeatable measurements and profiling evidence to find where software spends time or resources. Profiling records runtime activity such as CPU use, memory use, database work, or network delays.

laolaoshiren/claude-code-skills-zh · 78 tokens

log-analyzer

A log-analysis helper that reads application and system logs to find unusual patterns and likely causes. Logs are records of events such as errors, requests, warnings, and service activity.

laolaoshiren/claude-code-skills-zh · 24 tokens

bug-reproducer

Find likely software bugs in a codebase, rank concrete bug candidates, and prove or reject them with focused regression tests before proposing a fix. Also turn bug reports, stack traces, screenshots, failing behavior, support tickets, and regressions into minimal reproducible cases with red-to-green evidence. Use when…

AnastasiyaW/codex-claude-code-config · 147 tokens