verification-repair

verification-repair is a command for Claude Code from thixpin/pitway. It costs 0 tokens per session (534 once invoked), scanned A, original, MIT.

A narrowly controlled correction process for a completed task within an unfinished milestone. It requires approval that names the files or checks to change before the correction is committed or cancelled.

In plain words
What is it for?
Use it when verification finds a genuine, limited correction after a task is complete but before its milestone is closed.
Why use it?
It prevents late fixes from quietly expanding the task’s scope or bypassing review. The two-stage process records what was approved and what was changed.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Good fit Use it when verification finds a genuine, limited correction after a task…

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/thixpin/pitway/verification-repair
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.

Clone the repo
git clone --depth 1 https://github.com/thixpin/pitway

Made for: Claude Code.

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 verification-repair

README.md
[![agentmods](https://agentmods.dev/badge/commands/thixpin/pitway/verification-repair.svg)](https://agentmods.dev/commands/thixpin/pitway/verification-repair)
Your own site
<a href="https://agentmods.dev/commands/thixpin/pitway/verification-repair"><img src="https://agentmods.dev/badge/commands/thixpin/pitway/verification-repair.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 534 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.
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 $0.00000 $0.00534
Opus 5 $0.00000 $0.00267
Sonnet 5 $0.00000 $0.00107
Haiku 4.5 $0.00000 $0.00053

Measured 7d ago against content hash fcbcc2378ea4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

verification-repair 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 7d 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.

src/integrations/claude/commands/verification-repair.md · 43 lines

What it actually says

verification-repair

Role: Main Agent (approve) · Orchestrator (propose, commit, cancel)

pitway verification-repair approve <milestone> [--file <path> ...] [--check <id> ...] --change-log <text> [--json]
pitway verification-repair commit <milestone> <vr-id> [--json]
pitway verification-repair cancel <milestone> <vr-id> [--json]

Use only for the exact narrow window M008's 6f8b5e6 exception covered: every non-cancelled task in the target milestone is completed, the milestone itself is still in_progress (not yet milestone-completed), and a genuine correction (not new scope) needs to land against it. Never a substitute for task-level TDD while a task is still in flight.

Two phases, always in this order:

  • verification-repair approve <milestone> --file <path>... --check <id>... --change-log <text> — run this BEFORE any implementation edit. Running it against the exact file/check list is itself the approval; it allocates a durable VR id and rejects an empty/duplicate list, a file path outside the repo, or an unknown check id. Command, manual, and review checks are all valid scope (B040). At most one repair may be pending per milestone.
  • verification-repair commit <milestone> <vr-id> — run only after the edits are made. Reruns every approved command check; a manual/review check is satisfied only by a developer verdict recorded with verify <milestone> --check <id> --pass after the approval (a re-record is the honest equivalent of a rerun). Refuses the whole commit (repair stays pending) if any check fails or lacks its re-record, or if the dirty tree holds anything outside the approved scope.

verification-repair cancel <milestone> <vr-id> abandons a still-pending repair.

See ../protocol-driver.md. Run pitway verification-repair --help or pitway verification-repair <subcommand> --help for flags and details.

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. 7d ago First seen · 43 lines · 0 tokens per session scan A fcbcc2378ea4

Subscribe to this mod's changes

verification-repair is a command published in the GitHub repository thixpin/pitway (19 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 534 tokens. 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 2026-08-30.