plan-reviewer

plan-reviewer is an agent for coding agents from alicicek/tale-mode. It costs 65 tokens per session (408 once invoked), scanned A, original, MIT.

An adversarial review agent for coding plans and substantial changes. It reads the actual files and sources, then reports specific ways the work could fail.

In plain words
What is it for?
Reviewing a plan or code diff before release, checking claims against the code, and producing numbered findings with evidence and suggested safeguards.
Why use it?
It helps expose blind spots such as security leaks, race conditions, broken assumptions, ordering mistakes, and tests that miss important failures.

Agent

Part of the tale-mode plugin — 6 skills, 2 commands, 1 agent 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/alicicek/tale-mode/plan-reviewer
Clone the repo
git clone --depth 1 https://github.com/alicicek/tale-mode

Or install tale-mode, the plugin that ships this one along with the rest of its 6 skills, 2 commands, 1 agent.

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-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/alicicek/tale-mode/plan-reviewer.svg)](https://agentmods.dev/agents/alicicek/tale-mode/plan-reviewer)
Your own site
<a href="https://agentmods.dev/agents/alicicek/tale-mode/plan-reviewer"><img src="https://agentmods.dev/badge/agents/alicicek/tale-mode/plan-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 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 5.1 $0.00065 $0.00408
Opus 5 $0.00032 $0.00204
Sonnet 5 $0.00013 $0.00082
Haiku 4.5 $0.00006 $0.00041

Measured 5d ago against content hash b19f72ed9349, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

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.

plugins/tale-mode/agents/plan-reviewer.md · 35 lines

What it actually says

You review a plan or a diff BEFORE it ships. Assume the author is over-confident and was reviewing their own work — so they could not see their own blind spots. That blind spot is your job.

Do not trust the plan's claims. Read the actual code / files / sources it depends on and verify at the line level. Then hunt for concrete failure modes:

  • What breaks at a call site, caller, or contract the author didn't check?
  • Which invariant does a step threaten (security, privacy, data integrity, money / idempotency, public API or URL stability, concurrency)?
  • What ordering, dependency, or race is wrong?
  • Which claim is stale or false vs. the actual source? (quote the line that proves it)
  • What's asserted "done / safe / trivial / already handled" with no evidence?
  • Did the author turn a settled plan item into an "open decision", or mark an engineering alternative as "Recommended" when the active plan says otherwise?
  • What will the proposed verification NOT catch?

Return a numbered list. Each finding: trap (one line) · proof (file:line or command output) · severity (critical/high/medium) · the concrete fix or the gate that would catch it.

Be specific and code-grounded — no generic advice. If a candidate is only theoretical, label it so. If the work is genuinely sound, say that plainly and stop — do not invent problems to look productive.

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 · 35 lines · 65 tokens per session scan A b19f72ed9349

Subscribe to this mod's changes

plan-reviewer is an agent published in the GitHub repository alicicek/tale-mode (36 stars, last pushed 2mo ago), licensed MIT. It adds 65 tokens to every session and 408 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

quality-fixer

Specialized agent for verifying software projects and fixing quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, correctness, or fix requests.

shinpr/claude-code-workflows · 44 tokens

solver

Derives multiple solutions for verified causes and analyzes tradeoffs. Use when root cause verification has concluded, or when "solution/how to fix/fix method/remedy" is mentioned. Focuses on solutions from given conclusions without investigation.

shinpr/claude-code-workflows · 48 tokens

verifier

Critically evaluates investigation results, checks path coverage, and validates failure points using Devil's Advocate method. Use when investigation has completed, or when "verify/validate/double-check/confirm findings" is mentioned. Focuses on verification and conclusion derivation.

shinpr/claude-code-workflows · 54 tokens

code-reviewer

Reviews completed implementation for governing-source compliance, scope economy, repository quality policy, and material code correctness. Use after implementation or when review/implementation check/compliance is requested.

shinpr/claude-code-workflows · 38 tokens

code-verifier

Verifies repository-backed claims and implementation feasibility in PRDs, Design Docs, or Work Plans. Use before document review, after implementation, or for reverse-engineered artifact verification.

shinpr/claude-code-workflows · 39 tokens

release-manager

Cuts a brooks-lint release: sets the version in package.json, propagates it across the four plugin manifests and every version-bearing text file via npm run bump, writes the CHANGELOG entry, re-validates, then commits, pushes to main, tags, and publishes the GitHub release. Final pipeline stage of the brooks-harness…

hyhmrright/brooks-lint · 85 tokens