plan-freeze

A command that commits a feature’s specification and implementation plan to a separate branch and opens a pull request for review.

In plain words
What is it for?
Use it to freeze a feature plan for human review, especially when the plan’s assessment recommends waiting before implementation.
Why use it?
It creates a review checkpoint before implementation begins, so people can agree on the plan first.

Command for Claude Code

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 commands/pluginslab/wp-agentic-kit/plan-freeze
Clone the repo
git clone --depth 1 https://github.com/pluginslab/wp-agentic-kit

Made for: Claude Code.

Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 372 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 $0.00052 $0.00372
Opus 5 $0.00026 $0.00186
Sonnet 5 $0.00010 $0.00074
Haiku 4.5 $0.00005 $0.00037

Measured yesterday against content hash 44ab72e1264f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-freeze 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 yesterday.

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.

.claude/commands/plan-freeze.md · 20 lines

What it actually says

Plan freeze

Run the plan-freeze flow for the active feature (or the slug provided as $ARGUMENTS if specified). This command is meant for plans whose Freeze assessment recommends freeze, or for explicit human override of a "proceed" recommendation. If the assessment says "proceed" and no override was given, ask the user to confirm before proceeding.

  1. If $ARGUMENTS is empty, locate the active feature: the most recently modified .claude/plans/features/*/progress.md whose status: is not complete|done|shipped|archived|completed. Use its directory's basename as the slug.
  2. If $ARGUMENTS is non-empty, use it as the slug. Verify .claude/plans/features/$ARGUMENTS/spec.md and plan.md both exist; refuse if not.
  3. Confirm the working tree has no changes outside .claude/plans/features/<slug>/. If it does, ask the user to commit or stash them first — scripts/open-plan-pr.sh will refuse otherwise.
  4. Run:
    ./scripts/open-plan-pr.sh <slug>
    
  5. Report the PR URL the script printed.
  6. Remind the user: do not start implementing yet. Phase 3 begins after a human merges the plan PR.
  7. Offer to dispatch the plan-reviewer sub-agent against the PR for a read-only audit before requesting human review.
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. yesterday First seen · 20 lines · 52 tokens per session scan A 44ab72e1264f

Subscribe to this mod's changes

plan-freeze is a command published in the GitHub repository pluginslab/wp-agentic-kit (18 stars, last pushed 2mo ago), licensed MIT. It adds 52 tokens to every session and 372 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.