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.
npx skills add ralfyishere/rules-with-receipts --skill error-recoverygit clone --depth 1 https://github.com/ralfyishere/rules-with-receiptsWrote 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.
[](https://agentmods.dev/skills/ralfyishere/rules-with-receipts/error-recovery)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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.
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.
- 10d ago First seen · 77 lines · 0 tokens per session scan A d720b31dcb78
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.
Other skills, from other repositories
code-review
Reviews code for bugs, security issues, and best practices.
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.
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.
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.
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.
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…