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 HirogaKatageri/hirokata --skill verify-and-fixgit clone --depth 1 https://github.com/HirogaKatageri/hirokataWrote 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/hirogakatageri/hirokata/verify-and-fix)<a href="https://agentmods.dev/skills/hirogakatageri/hirokata/verify-and-fix"><img src="https://agentmods.dev/badge/skills/hirogakatageri/hirokata/verify-and-fix/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/hirogakatageri/hirokata/verify-and-fix"><img src="https://agentmods.dev/badge/skills/hirogakatageri/hirokata/verify-and-fix.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 | $0.00136 | $0.02755 |
| Opus 5 | $0.00068 | $0.01378 |
| Sonnet 5 | $0.00027 | $0.00551 |
| Haiku 4.5 | $0.00014 | $0.00276 |
Grade A, and why
verify-and-fix 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 12d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify and Fix
Diagnoses and fixes reported errors through a structured end-to-end workflow: gather context via your error-verification guide, investigate configured log and code sources, propose ranked solutions, then apply a test-driven fix.
Workflow Overview
The skill runs five phases in sequence:
- Phase 0 — Guide Gate: detect or create the project's error-verification guide in
CLAUDE.md - Phase 1 — Error Input: collect the error artifact from the triggering message
- Phase 2 — Investigation: read
references/investigation.mdand perform source investigation - Phase 3 — Solution Proposal: produce a findings report, then a ranked solution set (defined in the same reference)
- Phase 4 — TDD Fix: read
references/tdd-fix.mdand apply a test-driven fix for the selected solution
Phases 2–4 are detailed in the reference files. Read each reference when you reach it — do not read them in advance.
Phase 0: Guide Gate (US-1, US-6)
0.1 Detect the Guide
- Read
CLAUDE.mdif it exists. Look for a level-2 heading exactly## Error Verification Guide. - If that heading is absent (or
CLAUDE.mddoes not exist), readAGENTS.mdif it exists and look for the same heading. TreatAGENTS.mdas read-only — never write to it.
0.2 Branch on Detection Result
- Guide found in
CLAUDE.mdand well-formed → state "Using your existing error-verification guide." and skip to Phase 1. - Guide found in
AGENTS.mdbut not inCLAUDE.md→ use it for this invocation, but inform the user that the guide belongs inCLAUDE.mdand offer to copy it there. - Guide found in both with conflicting content → prefer the
CLAUDE.mdversion, note the conflict, and suggest removing theAGENTS.mdduplicate. - Guide missing, empty, or malformed in all locations → run the setup interview (§ 0.3).
- User explicitly asked to update (phrases like "update my error guide", "re-run error setup") → run the setup interview pre-filled with current values, then overwrite the
## Error Verification Guidesection inCLAUDE.md.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 189 lines · 136 tokens per session scan A 2b027d62c0c5
verify-and-fix is a skill published in the GitHub repository HirogaKatageri/hirokata (5 stars, last pushed 4d ago), licensed MIT. It adds 136 tokens to every session and 2,755 once invoked, about $0.0007 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
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.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
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…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.