planr-reviewer

planr-reviewer is an agent for coding agents from instructa/planr. It costs 31 tokens per session (298 once invoked), scanned A, original, MIT.

An independent checker for one Planr review gate, a saved checkpoint where a coding task is judged. It inspects the actual code changes and evidence, then records a verdict.

In plain words
What is it for?
Use it to audit a specific Planr review gate, replay selected checks, record clear findings, and close the gate with the checker's identity.
Why use it?
It prevents the person who made the changes from judging their own work and prevents summaries or old records from being treated as proof.

Agent

Part of the planr plugin — 10 skills, 2 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 agents/instructa/planr/planr-reviewer
Clone the repo
git clone --depth 1 https://github.com/instructa/planr

Or install planr, the plugin that ships this one along with the rest of its 10 skills, 2 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 planr-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/instructa/planr/planr-reviewer.svg)](https://agentmods.dev/agents/instructa/planr/planr-reviewer)
Your own site
<a href="https://agentmods.dev/agents/instructa/planr/planr-reviewer"><img src="https://agentmods.dev/badge/agents/instructa/planr/planr-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 298 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 $0.00031 $0.00298
Opus 5 $0.00015 $0.00149
Sonnet 5 $0.00006 $0.00060
Haiku 4.5 $0.00003 $0.00030

Measured 4d ago against content hash 7e91c6159169, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

planr-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 4d 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.

plugins/planr/agents/planr-reviewer.md · 22 lines

What it actually says

Use the preloaded planr-review skill exactly as written for the single ReviewGate id you are given. Continue only from work_packet.kind: "review_gate" and use its canonical execution_state with schema planr.execution_state.v2; its budget projection is opaque and generated roles must not recompute budget policy. Never infer review state from map work types or historical metadata. You did not write this code; audit it like an owner. Inspect the actual diff, validate exact-source receipts, and selectively replay only cheap, missing, failing, or explicitly high-risk evidence instead of trusting the worker's summary. Close the gate with planr review close <review-gate-id> --verdict ... --reviewer <your-id> and always pass --reviewer explicitly (e.g. checker-1): shell exports do not survive between tool calls, and a gate closed under the wrong identity fails the independence check. Findings must be specific and actionable. Do not edit implementation files; your only writes are Planr ReviewGate commands.

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. 4d ago First seen · 22 lines · 31 tokens per session scan A 7e91c6159169

Subscribe to this mod's changes

planr-reviewer is an agent published in the GitHub repository instructa/planr (71 stars, last pushed 7d ago), licensed MIT. It adds 31 tokens to every session and 298 once invoked, about $0.0002 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 2026-08-30.