A command that checks a drafted master plan against a fixed review checklist and reports a pass or fail result. With approval, it can add a dated verified marker to the plan.

Use it to review a master planning document and optionally record that it passed the checklist.

It exposes missing sections, vague dependencies, unsupported references, or phases that cannot be acted on before the plan is used. It can also find the likely plan file when no path is supplied.

plan-verify — Command for Claude Code by oborchers/fractional-cto

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/oborchers/fractional-cto

Made for: Claude Code.

Or install planning-tools, the plugin that ships this one along with the rest of its 5 skills, 7 commands, 3 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/oborchers/fractional-cto/plan-verify/github.svg)](https://agentmods.dev/commands/oborchers/fractional-cto/plan-verify)

Your own site

<a href="https://agentmods.dev/commands/oborchers/fractional-cto/plan-verify"><img src="https://agentmods.dev/badge/commands/oborchers/fractional-cto/plan-verify/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/oborchers/fractional-cto/plan-verify"><img src="https://agentmods.dev/badge/commands/oborchers/fractional-cto/plan-verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,602 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.

Model	Per session	Once invoked
Fable 5.1	$0.00034	$0.01602
Opus 5.5	$0.00014	$0.00641
Sonnet 5.5	$0.00007	$0.00320
Haiku 4.5	$0.00003	$0.00160

Measured 5d ago against content hash 99116d5f6ba1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

plan-verify 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.

planning-tools/commands/plan-verify.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are auditing a master planning document against the plan-verification-checklist skill. The audit emits Critical/Important/Suggestion findings with a PASS/FAIL verdict. On PASS, you may append a Verified marker to the plan's context block — a - **Verified:** YYYY-MM-DD bullet (v0.3.3+), or a > **Verified:** YYYY-MM-DD line on a legacy blockquote plan — but only with the user's explicit approval.

Input: $ARGUMENTS — the path to the master plan.

If arguments are empty, resolve the plan via the binary-confirm pattern (avoids AskUserQuestion's 4-option cap, which would overflow on the common case of 8+ candidate plans across context/tickets/, docs/plans/, .claude/plans/master/):

Glob context/tickets/*-PLAN.md, docs/plans/*.md, .claude/plans/master/*.md (whichever exists) under the git root. Sort by modification time, newest first.
0 candidates: error with the three searched paths and a hint to pass an explicit path.
1 candidate: use it. Print the resolved path. Continue to Step 1.
2+ candidates: print the candidate list as plain text with the most-recently-modified at the top:
```
N candidate master plans found (most-recent first):
  1. context/tickets/CI-21-PLAN.md — modified <date>
  2. context/tickets/CI-08-LITE-PLAN.md — modified <date>
  ...
  N. docs/plans/foo.md — modified <date>
```
Then call AskUserQuestion with exactly two options:
- Option 1 (recommended): "Verify the most-recently-modified plan (#1)" — description: "Audit <path of #1>."
- Option 2: "Cancel — I'll re-run with explicit path" — description: "Stop. Re-run /planning-tools:plan-verify to target a specific plan."
Branch on the answer. On Proceed, use the #1 (most-recently-modified) plan and continue to Step 1. On Cancel, stop.

Step 1 — Dispatch the verifier agent

Dispatch the plan-verifier agent (sonnet). The agent receives:

The plan path to audit
An output file path for the verification report (e.g., /tmp/plan-verify/<plan-basename>-verification.md)
Today's date

The agent reads the plan-verification-checklist skill, audits the plan against every dimension, and writes a structured report. It returns a one-paragraph summary: total findings by severity, the verdict (PASS or FAIL), top 3 highest-impact fixes, and the report path.

Do not re-read the full plan in the main conversation. The agent does that.

Read the full file on GitHub · 109 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.

5d ago First seen · 109 lines · 34 tokens per session scan A 99116d5f6ba1

Subscribe to this mod's changes

plan-verify is a command published in the GitHub repository oborchers/fractional-cto (32 stars, last pushed 5d ago), licensed MIT. It adds 34 tokens to every session and 1,602 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-13.

Planning

plan-verify

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Step 1 — Dispatch the verifier agent

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

converge

implement

speckit.bug.fix