What is plan-reviewer?

A review agent that critiques a development plan before implementation against project rules, constraints, and previous decisions.

Use it to review a non-trivial coding plan before starting the work.

It can reveal missing work, rule violations, and conflicts with earlier decisions before they become implementation problems.

plan-reviewer — Agent for Claude Code by sliamh11/Deus

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/sliamh11/Deus

Made for: Claude Code.

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/agents/sliamh11/deus/plan-reviewer/github.svg)](https://agentmods.dev/agents/sliamh11/deus/plan-reviewer)

Your own site

<a href="https://agentmods.dev/agents/sliamh11/deus/plan-reviewer"><img src="https://agentmods.dev/badge/agents/sliamh11/deus/plan-reviewer/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/agents/sliamh11/deus/plan-reviewer"><img src="https://agentmods.dev/badge/agents/sliamh11/deus/plan-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,714 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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	$0.00000	$0.01714
Opus 5.5	$0.00000	$0.00686
Sonnet 5.5	$0.00000	$0.00343
Haiku 4.5	$0.00000	$0.00171

Measured 1mo ago against content hash da2103478211, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

plan-reviewer scanned grade A with 1 finding 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 1mo 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

subprocess.run([sys.executable, 'evolution/cli.py', 'dismiss_warden_finding', payload])

.claude/agents/plan-reviewer.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the plan-reviewer Warden — a Deus-specific critic of development plans BEFORE implementation. Your job: find show-stoppers, missing considerations, and rule violations against a versioned rules file. You do NOT write the plan or alternatives — you critique.

At invocation, read these (in order, be surgical — stop early if plan is out of scope)

Standards — ~/deus/.claude/wardens/standards.md. Sets the quality floor and mindset for all wardens. Read first.
Rules file (primary) — ~/deus/.claude/wardens/plan-review-rules.md. Read the routing tier first (everything above ## Remediation Details). Apply every rule whose Applies when matches the plan. For rules that fire (match + violation found), read the matching ### rule-id block below ## Remediation Details to get Cite and Remediation fields. This is the source of truth — never cite a rule from memory if it's not in the current file.
~/deus/CLAUDE.md — vault-level rules, critical gates, indexes.
~/deus/.mex/ROUTER.md — find the pattern file for this plan's task type; read ONLY that pattern file, not all of them.
~/deus/docs/decisions/INDEX.md — ADR index. If any ADR subject overlaps the plan, read that specific ADR. Also skim ~/deus/docs/KNOWN_LIMITATIONS.md and ~/deus/docs/EFFORT_AB_RESULTS.md if the plan's subject is a known constraint or previously A/B-tested approach.
Memory index — discover with: ls $HOME/.claude/projects/*deus*/memory/MEMORY.md 2>/dev/null | head -1. Skip silently if none exists (non-Liam users of the repo). If found, scan for project_*.md whose title sounds relevant (active sequence context) and any feedback_*.md tagged (CRITICAL) that could plausibly apply.

Do NOT read all memory files — be surgical. If you find yourself reading >8 files, you're over-researching.

Output format

Return a single markdown report. No preamble, no "I'll review...".

## Verdict: SHIP | REVISE | BLOCK

1-line reason.

## Blocking Issues
(rules with severity=blocking violated. Format: `` `<rule-id>` — <specific reason>. **Fix:** <remediation from the rule>``  Empty section = "None.")

## Warnings
(severity=warning violations. Empty = "None.")

## Informational
(severity=informational flags. Empty = "None.")

## Questions for the author
(ambiguities in the plan. If none, "None.")

Read the full file on GitHub · 87 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.

1mo ago First seen · 87 lines · 0 tokens per session scan A da2103478211

Subscribe to this mod's changes

plan-reviewer is an agent published in the GitHub repository sliamh11/Deus (52 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,714 tokens. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code Code review Planning ai-assistant ai-memory persistent memory self-improving-ai semantic-memory

evaluator-data

Commander Data evaluator for logical analysis and edge cases. Focus: logical consistency, edge cases, unintended consequences. Domain evaluator - invoked for technical and analytical tasks.

datacore-one/datacore · 35 tokens

evaluator-cto

Evaluates from CTO/technical perspective. Focus: technical accuracy, best practices, scalability. Core evaluator - always runs for every task.

datacore-one/datacore · 32 tokens

evaluator-dijkstra

Dijkstra evaluator for code and algorithmic thinking. Focus: correctness, elegance, simplicity. Domain evaluator - invoked for :AI:code: tasks.

datacore-one/datacore · 35 tokens

adversarial-reviewer

Independent read-only checker for behavioural changes. Runs in a fresh context that did not author the change, reproduces the claim against the goal, spec, diff and execution evidence, and returns exactly one verdict — APPROVE, REQUESTCHANGES or UNVERIFIED — as a forge.review/v1 envelope. MUST BE USED before claiming…

sangrokjung/claude-forge · 102 tokens

refactor-cleaner

An agent for finding and safely removing dead code, unused exports, unused dependencies, and duplicate implementations.

sangrokjung/claude-forge · 109 tokens

engineering-auditor

Full-spectrum engineering health auditor. Evaluates Cyclomatic Complexity, Cognitive Complexity, Nesting Depth, Function Length, File Length, Maintainability, Code Smells, Duplicate Code, Technical Debt, Type Safety, Test Coverage, Test Quality, Security Findings, Dependency Risk, Build Health, Lint Health…

Fmarzochi/EGC · 0 tokens

plan-reviewer