verify-fix

verify-fix is a command for Claude Code from TechNickAI/ai-coding-config. It costs 22 tokens per session (993 once invoked), scanned A, original, MIT.

A command for checking that a recent code fix really works through tests, live pages, API requests, or configuration checks.

In plain words
What is it for?
It verifies named behaviors or inferred recent fixes across test suites, web interfaces, API endpoints, and configuration files.
Why use it?
It prevents a fix from being declared complete when only the code changed but the user-facing behavior still fails.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is go test ./pkg/... -run TestAffectedFunction.

Part of the ai-coding-config plugin — 15 skills, 21 commands, 28 agents, 3 hooks shipped together

Good fit It verifies named behaviors or inferred recent fixes across test suites, web interfaces, API endpoints, and configuration files.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/TechNickAI/ai-coding-config
agentmods
npx agentmods add commands/technickai/ai-coding-config/verify-fix

Made for: Claude Code.

Or install ai-coding-config, the plugin that ships this one along with the rest of its 15 skills, 21 commands, 28 agents, 3 hooks.

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 verify-fix

README.md
[![agentmods](https://agentmods.dev/badge/commands/technickai/ai-coding-config/verify-fix/github.svg)](https://agentmods.dev/commands/technickai/ai-coding-config/verify-fix)
Your own site
<a href="https://agentmods.dev/commands/technickai/ai-coding-config/verify-fix"><img src="https://agentmods.dev/badge/commands/technickai/ai-coding-config/verify-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.

agentmods 80×15 button for verify-fix

Your own site · 80×15
<a href="https://agentmods.dev/commands/technickai/ai-coding-config/verify-fix"><img src="https://agentmods.dev/badge/commands/technickai/ai-coding-config/verify-fix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 993 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00022 $0.00993
Opus 5.5 $0.00009 $0.00397
Sonnet 5.5 $0.00004 $0.00199
Haiku 4.5 $0.00002 $0.00099

Measured 25d ago against content hash 273966e49033, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verify-fix scanned grade A with 1 finding 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 25d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s http://localhost:3000/affected-page | head -20
plugins/core/commands/verify-fix.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify Fix Command

Core principle: A fix isn't fixed until you've seen it work.

  • /verify-fix - Verify the most recent fix (infer from context)
  • /verify-fix "login redirect works" - Verify specific behavior
  • /verify-fix auth tests - Run auth-related tests

Tests exist: Run the relevant test file or test suite.

# TypeScript/JavaScript
pnpm test path/to/affected.test.ts
npm test -- --testPathPattern="ComponentName"
vitest run src/component.test.tsx

# Python
pytest path/to/test_module.py -v

# Go
go test ./pkg/... -run TestAffectedFunction

UI changes: Start dev server and verify visually or fetch the page.

# Verify page loads correctly
curl -s http://localhost:3000/affected-page | head -20

# Or use MCP Playwright tools for visual verification
mcp__plugin_playwright_playwright__browser_navigate to affected URL
mcp__plugin_playwright_playwright__browser_snapshot to capture state

API changes: Hit the endpoint and check the response.

curl -X POST http://localhost:3000/api/endpoint \
  -H "Content-Type: application/json" \
  -d '{"test": "data"}'

Config changes: Verify the config loads without error.

node -e "require('./config')"
python -c "from config import settings; print(settings)"

Build/compile: Verify the build succeeds.

pnpm build
npm run build
go build ./...
✓ Verified: [what was tested]
  Ran: [command]
  Result: [specific outcome - N tests passed, page loads, response correct]
  Evidence: [URL, test output, or response snippet]

Fix confirmed: [specific claim about what's now working]

On failed verification:

✗ Verification failed
  Ran: [command]
  Result: [what happened]
  Error: [specific error message or unexpected behavior]

The fix is NOT confirmed. [Next action: investigating X / trying Y / need more info]

After successful verification, use confident language:

  • "Verified: the login redirect now works correctly"
  • "Fix confirmed: tests pass and the page loads"

Claim success only with specific evidence. Epistemic honesty preserves trust.

If verification fails, continue debugging rather than reporting success.

  • Tests pass that directly exercise the changed code paths
  • Live request returns the expected response through the modified code
  • UI renders correctly when displaying the fixed functionality
  • Build completes without errors affecting the changed files
  • The specific broken behavior is now demonstrably working

The standard: observe the fix working through code paths that exercise it. A passing test suite verifies the fix when those tests cover the changed behavior.

  • Document what verification is needed in your response
  • Explain to the user what they should verify manually
  • Be explicit that the fix is unverified pending these checks

Read the full file on GitHub · 155 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. 25d ago First seen · 155 lines · 22 tokens per session scan A 273966e49033

Subscribe to this mod's changes

verify-fix is a command published in the GitHub repository TechNickAI/ai-coding-config (24 stars, last pushed 26d ago), licensed MIT. It adds 22 tokens to every session and 993 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-22.