agentmods.dev

moth-verify-fix

A workflow for checking whether a bug fix actually works by running the narrowest relevant test or development command.

In plain words
What is it for?
Use it after changes to tests, builds, types, lint rules, runtime behavior, frameworks, or packages, then record the exact verification result.
Why use it?
It prevents a fix from being declared successful based only on inspection or assumption.

Skill for Claude CodeCodex

Part of the moth plugin — 3 skills shipped together

2 4mo ago A scan 49 tokens original MIT
View the source file stfade/moth
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.

agentmods
npx agentmods add skills/stfade/moth/moth-verify-fix
Any agent
npx skills add stfade/moth --skill moth-verify-fix
Clone the repo
git clone --depth 1 https://github.com/stfade/moth

Made for: Claude Code, Codex.

Or install moth, the plugin that ships this one along with the rest of its 3 skills.

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 362 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00049 $0.00362
Opus 5 $0.00024 $0.00181
Sonnet 5 $0.00010 $0.00072
Haiku 4.5 $0.00005 $0.00036

Measured 2d ago against content hash beae911f704c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

moth-verify-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 2d 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.

integrations/claude-code/skills/moth-verify-fix/SKILL.md · 33 lines

What it actually says

Moth Verify Fix

Command Choice

Choose the narrowest command that can disprove the fix:

  1. Original reproduction command when available.
  2. Focused test for the changed module or failing case.
  3. Typecheck for TypeScript type errors.
  4. Lint for ESLint or formatting-rule failures.
  5. Build only when the issue is build-time or no narrower check exists.

Workflow

  1. Run the smallest command that covers the changed behavior.
  2. If it fails, use the new output as the next Moth error context instead of guessing.
  3. If it passes, consider one broader command only when the change touched shared behavior.
  4. Follow the verified memory lifecycle: analyze_error -> apply/attempt fix -> run verification command -> call remember_fix_result with verification_command and verification_result.
  5. Call remember_fix_result with the exact fix attempted, the concrete verification command that actually ran, and verification_result of passed or failed.

Guardrails

  • Do not call a fix successful without a relevant command or reproduction result.
  • Do not call remember_fix_result for suggestions, unapplied changes, missing verification, ambiguous results, or guesses.
  • Do not call remember_fix_result unless a fix/change was actually attempted, the verification command was actually run, and verification produced a clear pass or failure.
  • Do not run unrelated expensive checks first.
  • Do not record secrets or full sensitive logs in fix memory.
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. 2d ago First seen · 33 lines · 49 tokens per session scan A beae911f704c

Subscribe to this mod's changes

moth-verify-fix is a skill published in the GitHub repository stfade/moth (2 stars, last pushed 4mo ago), licensed MIT. It adds 49 tokens to every session and 362 once invoked, about $0.0002 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.

Debuggingai-coding-agentbug-fixdeveloper-toolsmcpmodel-context-protocol
Related

Other skills, from other repositories

xcodebuildmcp-structured-output-review

Use when reviewing XcodeBuildMCP structured output schema changes, schema versioning, manifest outputSchema metadata, and JSON fixture compatibility.

getsentry/XcodeBuildMCP · 37 tokens

telnyx-messaging-hosted-curl

Set up hosted SMS numbers, toll-free verification, and RCS messaging. Use when migrating numbers or enabling rich messaging features. This skill provides REST API (curl) examples.

team-telnyx/ai · 45 tokens

opik-diagnose

Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…

comet-ml/opik-mcp · 147 tokens

cortex-automate

Set up automation — prospective memory triggers, neuro-symbolic rules, and CLAUDE.md sync. Use when the user says 'remind me when', 'trigger when', 'create a rule', 'auto-remember', 'sync to CLAUDE.md', 'push insights', 'set up trigger', 'when I open this file', 'when this keyword appears', or when you want to…

cdeust/Cortex · 93 tokens

Presentations

Read, create or edit PowerPoint or Google Slides decks. Use for presentation, slide deck, PowerPoint, PPT, PPTX, or Google Slides requests.

rojim666/SztuCode · 35 tokens

devexpress-winforms-accordion

Expert skill for the DevExpress WinForms AccordionControl (DevExpress.XtraBars.Navigation.AccordionControl, DevExpress.Win.Navigation NuGet). Covers creating and populating accordion menus, data-driven element generation from collections, AccordionControlElement groups and items, content containers with embedded…

DevExpress/agent-skills · 188 tokens