fix-verification

fix-verification is a skill for Claude Code, Codex from VoDaiLocz/kilo-kit-mcp. It costs 49 tokens per session (2,315 once invoked), scanned A, original, Apache-2.0.

A checklist for confirming that a bug fix actually works and has not broken related behavior. It compares the original failure with the expected result and includes regression checks.

In plain words
What is it for?
Use it after implementing or reviewing a fix to reproduce the original bug, test the corrected behavior, run related checks, and look for regressions.
Why use it?
It prevents treating the disappearance of an error as proof that the problem is solved. It is especially useful when a fix is high-impact or earlier fixes failed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it after implementing or reviewing a fix to reproduce the original bug, test the corrected behavior, run related checks, and look for regressions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vodailocz/kilo-kit-mcp/verification
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 VoDaiLocz/kilo-kit-mcp --skill verification
Clone the repo
git clone --depth 1 https://github.com/VoDaiLocz/kilo-kit-mcp

Made for: Claude Code, Codex.

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 fix-verification

README.md
[![agentmods](https://agentmods.dev/badge/skills/vodailocz/kilo-kit-mcp/verification/github.svg)](https://agentmods.dev/skills/vodailocz/kilo-kit-mcp/verification)
Your own site
<a href="https://agentmods.dev/skills/vodailocz/kilo-kit-mcp/verification"><img src="https://agentmods.dev/badge/skills/vodailocz/kilo-kit-mcp/verification/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 fix-verification

Your own site · 80×15
<a href="https://agentmods.dev/skills/vodailocz/kilo-kit-mcp/verification"><img src="https://agentmods.dev/badge/skills/vodailocz/kilo-kit-mcp/verification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,315 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00049 $0.02315
Opus 5 $0.00024 $0.01157
Sonnet 5 $0.00010 $0.00463
Haiku 4.5 $0.00005 $0.00231

Measured 5d ago against content hash 9d42fa114457, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

fix-verification 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 5d 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.

skills/kilo-kit/debugging/verification/SKILL.md · 425 lines

How it starts

The opening of the file, as written. The whole thing — 425 lines — stays where its author put it; the contents beside it link to each section on GitHub.

✅ Fix Verification Skill

Philosophy: A bug isn't fixed until it's verified. Twice.

When to Use

Use this skill when:

  • You've implemented a bug fix
  • Someone else's fix needs verification
  • Deploying a fix to production
  • Bug was high-impact and needs thorough verification
  • Previous fixes for this bug have failed

Do NOT use this skill when:

  • Just exploring code (no fix yet)
  • Bug is trivial (e.g., typo fix)
  • Running standard CI (automated verification)

Prerequisites

Before starting:

  • Fix has been implemented
  • You know the expected behavior
  • You can reproduce the original bug (or have a failing test)
  • You have access to test environment

Process

Phase 1: DIRECT VERIFICATION 🎯

Goal: Confirm the fix addresses the exact reported issue.

Steps:

  1. Recreate the Original Bug Scenario

    Exact steps that caused the bug:
    1. [step 1]
    2. [step 2]
    3. [step 3]
    
    Expected result: [what should happen]
    Previous result: [what was happening - the bug]
    
  2. Execute Test with Fix Applied

    • Follow exact same steps
    • Document actual result
    • Compare to expected
  3. Verify the FIX, Not Just Absence of Error

    ❌ "It doesn't crash anymore" (incomplete)
    ✅ "It returns the expected user object with correct fields" (complete)
    
  4. Test Multiple Times

    • Run at least 3 times
    • Note any inconsistency

Verification Checklist:

  • Original bug scenario no longer produces error
  • Expected behavior now occurs
  • Result is consistent across multiple runs
  • All variations of bug scenario work

Phase 2: EDGE CASE VERIFICATION 🔲

Goal: Ensure fix works for edge cases and variations.

Steps:

  1. Identify Edge Cases
    edge_cases:
      boundary_values:
        - Empty input
        - Maximum length input
        - Minimum valid input
        - Just over limit
        - Just under limit
      
      special_inputs:
        - Null/undefined
        - Special characters
        - Unicode/emoji
        - Numbers as strings
        - Whitespace only
      
      state_variations:
        - First time user
        - Returning user
        - Admin user
        - Concurrent users
        - High load
    

Read the full file on GitHub · 425 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. 5d ago First seen · 425 lines · 49 tokens per session scan A 9d42fa114457

Subscribe to this mod's changes

fix-verification is a skill published in the GitHub repository VoDaiLocz/kilo-kit-mcp (26 stars, last pushed today), licensed Apache-2.0. It adds 49 tokens to every session and 2,315 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 2026-09-03.

Related

Other skills, from other repositories

browser-automation

Browser automation powers web testing, scraping, and AI agent.

hybridlabor-api/bdb-dev-optimized-agent-skills · 15 tokens

godmode-shipping

BDB Shipping Godmode, the final gatekeeper for production releases. Use when running pre-launch checks, feature-flag rollouts, or rollback planning under Spec-Driven Development before a release ships.

hybridlabor-api/bdb-dev-optimized-agent-skills · 45 tokens

integration-test-guard

Ensure MCP-server / API changes in the touchdesigner-mcp repo ship with integration-test coverage. Use when you modify the MCP server, tool definitions/handlers, the OpenAPI schema, the TD HTTP client, the transport layer, or the TD-side Python API (src/api, src/features/tools, src/server, src/tdClient, src/transport…

hybridlabor-api/bdb-dev-optimized-agent-skills · 130 tokens

touchdesigner-self-debug

A generic workflow for self-starting TouchDesigner via computer-use (or an already-running instance), loading mcpwebserverbase.tox, and verifying any TD-side Python change (td/modules/) directly from the Textport — reading back real TD runtime values and reconciling them. Use after changing TD-side code in the…

hybridlabor-api/bdb-dev-optimized-agent-skills · 134 tokens

tdmcp-test-coverage

Orchestrate any tdmcp test-coverage work: run the coverage harness, inspect coverage gaps, plan focused Vitest/msw or bridge tests, delegate coverage writers, verify coverage deltas, and re-run gates. Use whenever the user asks to raise coverage, add broad regression coverage, create a test harness, improve tests…

hybridlabor-api/bdb-dev-optimized-agent-skills · 86 tokens

td-feature-qa

Quality-assure integrated tdmcp features: run the four PR gates + recipe/bridge tests, cross-boundary coherence checks (tool schema↔CLI↔docs↔registry, operator↔createable, bridge↔client), and live TouchDesigner validation (preview + post-cook error check) when the bridge is reachable. Use when…

hybridlabor-api/bdb-dev-optimized-agent-skills · 105 tokens