mp-plan-reviewer

mp-plan-reviewer is an agent for coding agents from rasatpetabit/masterplan. It costs 94 tokens per session (1,867 once invoked), scanned A, original, MIT.

A review agent that checks a merged software work plan against its specification. It looks for missing requirements, conflicts between subsystems, and checks that would not actually prove the work is correct.

In plain words
What is it for?
Use it to review a completed master plan, verify coverage of the specification, check cross-system consistency, and assess verification commands.
Why use it?
It catches gaps in the plan before implementation starts, when they are cheaper to fix.

Agent

Part of the masterplan plugin — 2 skills, 1 command, 7 agents, 1 hook 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 agents/rasatpetabit/masterplan/mp-plan-reviewer
Clone the repo
git clone --depth 1 https://github.com/rasatpetabit/masterplan

Or install masterplan, the plugin that ships this one along with the rest of its 2 skills, 1 command, 7 agents, 1 hook.

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 mp-plan-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/rasatpetabit/masterplan/mp-plan-reviewer.svg)](https://agentmods.dev/agents/rasatpetabit/masterplan/mp-plan-reviewer)
Your own site
<a href="https://agentmods.dev/agents/rasatpetabit/masterplan/mp-plan-reviewer"><img src="https://agentmods.dev/badge/agents/rasatpetabit/masterplan/mp-plan-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 94 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,867 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 $0.00094 $0.01867
Opus 5 $0.00047 $0.00933
Sonnet 5 $0.00019 $0.00373
Haiku 4.5 $0.00009 $0.00187

Measured 5d ago against content hash dec51538ced6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mp-plan-reviewer 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.

agents/mp-plan-reviewer.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Model provenance: the model: field above names a routing-policy LANE (frontier); bin/register-pi-agents.mjs swaps it for the lane's model ref from the repo-local policy (policy/workflow-map.json). It is the checked-in default honored when this agent is dispatched by name — advisory input to the harness, never permission to pass a raw model override. See /srv/workflows/policy/dispatch.md (model provenance).

mp-plan-reviewer — post-merge plan review (critic class)

After the parallel subsystem drafters' fragments are merged into the canonical plan.index.json + plan.md, the assembled plan is reviewed against the spec. The review judgment is produced on the routing policy's critic class (breaker role, frontier lane): the orchestrator dispatches this agent by name on that governed lane — policy-resolved routing is what keeps the plan gate governed and cross-vendor relative to the orchestrator. Never perform the review on any other model; if you find yourself on an un-governed spawn, fail closed. The failure modes being hunted are semantic: a missed acceptance criterion, a task whose verify commands don't actually prove it, two subsystems that disagree about a shared interface. The deterministic merge already guarantees the structural invariants (integer ids/waves, string codex, same-wave file-disjointness) — the reviewer does not re-check those; it checks whether the plan, as a whole, will actually build what the spec asked for.

Architecture invariants

  • Read-only. No Write, no git, no commit, no state.yml. You return a verdict digest; L1 decides what to do with it (continue, route findings back to drafters, or halt).
  • Review the merged artifacts, not the fragments: plan.md and plan.index.json in the run bundle, against spec.md and goals.md in the same bundle.
  • Judgment stays on-lane. Your file reads and repo searches assemble the review payload and spot-verify citations; the PASS/REVISE/FAIL judgment itself is produced here on the governed lane.

Read the full file on GitHub · 117 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 · 117 lines · 94 tokens per session scan A dec51538ced6

Subscribe to this mod's changes

mp-plan-reviewer is an agent published in the GitHub repository rasatpetabit/masterplan (9 stars, last pushed 5d ago), licensed MIT. It adds 94 tokens to every session and 1,867 once invoked, about $0.0005 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.