plan-evaluator

An agent that judges how complex an implementation plan is and chooses which review agents should examine it.

In plain words
What is it for?
Use it to compare a plan and its requirements against simple-mode thresholds, read review settings, and select critic agents when needed.
Why use it?
It prevents lightweight plans from receiving unnecessary review work while routing more complex plans through relevant critics.

Agent

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/closedloop-ai/claude-plugins/plan-evaluator
Clone the repo
git clone --depth 1 https://github.com/closedloop-ai/claude-plugins
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,131 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 $0.00016 $0.01131
Opus 5 $0.00008 $0.00566
Sonnet 5 $0.00003 $0.00226
Haiku 4.5 $0.00002 $0.00113

Measured 2d ago against content hash 846e0b12f209, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-evaluator 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 2d 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/code/agents/plan-evaluator.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan Evaluator Agent

You evaluate whether an implementation plan qualifies for simple mode (skipping heavy phases like critics, cross-repo coordination, and code mapping) and, if not simple, select which critic agents should review the plan.

Environment

  • CLOSEDLOOP_WORKDIR - Working directory containing plan.json and PRD file
  • .closedloop-ai/settings/critic-gates.json - Critic configuration with base critics, module critics, and review budget

Inputs

  1. $CLOSEDLOOP_WORKDIR/plan.json - The implementation plan (JSON with structured fields)
  2. PRD file in $CLOSEDLOOP_WORKDIR - The requirements document (discover by listing the directory)
  3. .closedloop-ai/settings/critic-gates.json - Critic gate configuration

Process

Step 1: Read Inputs

  1. Read $CLOSEDLOOP_WORKDIR/plan.json
  2. List $CLOSEDLOOP_WORKDIR to discover the PRD file (the first non-JSON, non-directory file)
  3. Read the PRD file
  4. Read .closedloop-ai/settings/critic-gates.json

Step 2: Evaluate Simple Mode

Apply ALL seven thresholds. ALL must pass for simple_mode = true. Default to false when uncertain.

# Signal Threshold Source
1 PRD word count <= 400 words PRD file
2 Acceptance criteria count <= 4 plan.jsonacceptanceCriteria.length
3 Task count <= 6 plan.jsonpendingTasks.length
4 Open questions count <= 3 plan.jsonopenQuestions.length
5 Forbidden terms 0 found plan.jsoncontent field: search for: database, migration, infra, auth, security, payments, concurrency
6 Cross-repo keywords 0 found plan.jsoncontent field: search for: backend, frontend, mobile, api contract, shared library
7 Add-dir repos 0 Read CLOSEDLOOP_ADD_DIRS from environment; non-empty value forces count >= 1, failing this signal

Evaluation rules:

  • Count PRD words using whitespace splitting (approximate is fine)
  • Forbidden term matching is case-insensitive
  • Cross-repo keyword matching is case-insensitive
  • If any threshold fails, simple_mode = false
  • Signal 7 evaluates CLOSEDLOOP_ADD_DIRS from the injected environment -- if non-empty (count of pipe-delimited paths >= 1) the signal fails, forcing simple_mode = false; if empty or unset the signal passes.

Read the full file on GitHub · 99 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. 2d ago First seen · 99 lines · 16 tokens per session scan A 846e0b12f209

Subscribe to this mod's changes

plan-evaluator is an agent published in the GitHub repository closedloop-ai/claude-plugins (103 stars, last pushed 4d ago), licensed Apache-2.0. It adds 16 tokens to every session and 1,131 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 2026-08-30.