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 peteromallet/Arnold --skill superfixer_debuggit clone --depth 1 https://github.com/peteromallet/ArnoldWrote 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/peteromallet/arnold/superfixer_debug)<a href="https://agentmods.dev/skills/peteromallet/arnold/superfixer_debug"><img src="https://agentmods.dev/badge/skills/peteromallet/arnold/superfixer_debug/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/peteromallet/arnold/superfixer_debug"><img src="https://agentmods.dev/badge/skills/peteromallet/arnold/superfixer_debug.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 | $0.00155 | $0.10397 |
| Opus 5.5 | $0.00062 | $0.04159 |
| Sonnet 5.5 | $0.00031 | $0.02079 |
| Haiku 4.5 | $0.00015 | $0.01040 |
Grade A, and why
superfixer-debug 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 1mo 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 — 814 lines — stays where its author put it; the contents beside it link to each section on GitHub.
superfixer-debug
This skill replaces the former “stack of fixers” playbook. It is a decision and custody protocol, not a license to hand-advance a run. Its invariant is:
Evidence first → Sol scoping judgement → bounded DeepSeek V4 Flash evidence → Sol adjudication → canonical movement route → authoritative proof.
The fixer keeps custody until the accepted work is moving. A quarantine receipt is an evidence checkpoint, never a successful terminal outcome. When the preserved occurrence cannot safely resume, Sol must choose either an authority-approved migrated child or a canonical control-plane repair that makes the missing identity or authority durable, then the ordinary fixer must execute that route and prove cursor/milestone advancement. “No safe retry” is not a durable answer when the blocking seam is repairable. No route may fabricate history, bypass authority, or weaken a validator; a genuinely external approval remains an explicit gate with an active next-owner route.
No-op and coordination guards (run these first)
Before doing anything else:
- NO-OP: enumerate blocked/failed chains. If none are blocked or failed, report "No blocked/failed chains found; nothing to fix" and end. Do not invent work, fabricate a failure, or touch healthy/running chains.
- COORDINATION: check whether another fixer/repair is already active for the target chain. Use the RELIABLE signals (cloud status may not be available if the initiative has no cloud.yaml): (a) a FRESH managed subagent dir for this session under .megaplan/plans/resident-subagents/subagent-* (created in the last hours), (b) a held repair lease via inspect_repair_lock, or (c) a running subagent_worker process for that session. If any signal is active, report "Another fixer is already active for this chain; standing down" and end — never launch a competing fixer.
Epic-babysitting operational loop
This skill also covers "epic-babysitting": keeping the target chain actually moving, not just fixing one layer. Repeat this loop until the canonical milestone advances (index > 0):
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.
- 1mo ago First seen · 814 lines · 0 tokens per session scan A 6cd49b6e53da
superfixer-debug is a skill published in the GitHub repository peteromallet/Arnold (98 stars, last pushed 2d ago), licensed Apache-2.0. It adds 155 tokens to every session and 10,397 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-09-04.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.