plan-review

plan-review is a command for coding agents from infraspecdev/tesseract. It costs 28 tokens per session (408 once invoked), scanned A, original, MIT.

A command that sends a plan to several expert reviewers at the same time and creates a scored analysis plus an improved plan.

In plain words
What is it for?
Use it to evaluate a plan before implementation and save the review results and revised plan in a dated folder.
Why use it?
It exposes concerns that one reviewer might miss by checking infrastructure, security, developer experience, costs, and delivery readiness.

Command

Part of the dev-workflow plugin — 4 skills, 1 command, 5 agents shipped together

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 commands/infraspecdev/tesseract/plan-review
Clone the repo
git clone --depth 1 https://github.com/infraspecdev/tesseract

Or install dev-workflow, the plugin that ships this one along with the rest of its 4 skills, 1 command, 5 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.

agentmods badge for plan-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/infraspecdev/tesseract/plan-review.svg)](https://agentmods.dev/commands/infraspecdev/tesseract/plan-review)
Your own site
<a href="https://agentmods.dev/commands/infraspecdev/tesseract/plan-review"><img src="https://agentmods.dev/badge/commands/infraspecdev/tesseract/plan-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 408 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 $0.00028 $0.00408
Opus 5 $0.00014 $0.00204
Sonnet 5 $0.00006 $0.00082
Haiku 4.5 $0.00003 $0.00041

Measured 3d ago against content hash f3769985b908, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-review 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 3d 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.

dev-workflow/commands/plan-review.md · 42 lines

What it actually says

/plan-review

Run a multi-persona plan review. This command dispatches 3-5 expert reviewer agents in parallel to evaluate a plan document, then produces a scored analysis and enhanced plan.

Usage

/plan-review [path-to-plan]

If no path is provided, auto-detect the most recently generated plan document in the working directory.

Process

  1. Locate the plan — use the provided path or auto-detect recent plan files (*plan*.html, *plan*.md)
  2. Read the plan — load the full document content
  3. Invoke the plan-review skill — the skill handles persona selection, parallel dispatch, scoring, and output generation
  4. Write output — results go to review/<YYYY-MM-DD>-<topic-slug>/analysis.md and plan.md

Reviewers

Reviewer Focus Weight
Cloud Architect Infrastructure, scalability, HA, operational readiness 1.0
Security Engineer Security, threat modeling, testability, validation 1.0
DX Engineer Plan clarity, actionability, software architecture 1.0
Cost/FinOps Cost awareness, right-sizing, environment tiering 0.7
Agile Coach Sprint-readiness, story quality, dependencies 0.7

Not all reviewers run every time — the skill dynamically selects 3-5 based on plan content.

Output

  • review/<date>-<slug>/analysis.md — scored evaluation with per-persona grades, consolidated recommendations (P0/P1/P2)
  • review/<date>-<slug>/plan.md — enhanced plan with review feedback applied
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. 3d ago First seen · 42 lines · 28 tokens per session scan A f3769985b908

Subscribe to this mod's changes

plan-review is a command published in the GitHub repository infraspecdev/tesseract (5 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 408 once invoked, about $0.0001 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.