A terminal-based plan-review workflow that puts open decisions in a Markdown file for the user to answer in Vim. Coding starts only after every question has an answer.

It is for non-trivial tasks with multiple decisions or implementation steps, especially when the user wants to review and revise a plan directly in the terminal.

It gathers several decisions in one reviewable place instead of resolving them one at a time in chat. This makes the agreed plan explicit before implementation begins.

plangate — Skill for Claude Code and Codex by ParthGanatra

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.

Any agent

npx skills add ParthGanatra/agent-skills --skill plangate

Clone the repo

git clone --depth 1 https://github.com/ParthGanatra/agent-skills

Made for: Claude Code, Codex.

Its marketplace also offers this one on its own, as the plugin plangate — /plugin install plangate after adding the marketplace above.

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/skills/parthganatra/agent-skills/plangate/github.svg)](https://agentmods.dev/skills/parthganatra/agent-skills/plangate)

Your own site

<a href="https://agentmods.dev/skills/parthganatra/agent-skills/plangate"><img src="https://agentmods.dev/badge/skills/parthganatra/agent-skills/plangate/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/skills/parthganatra/agent-skills/plangate"><img src="https://agentmods.dev/badge/skills/parthganatra/agent-skills/plangate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 131 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,898 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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	$0.00131	$0.01898
Opus 5.5	$0.00052	$0.00759
Sonnet 5.5	$0.00026	$0.00380
Haiku 4.5	$0.00013	$0.00190

Measured 2mo ago against content hash 0ae009b55e2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

plangate 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 2mo ago.

The scan reads SKILL.md. This mod also ships 4 executable files (nudge-reload.sh, open-plan.sh, prune-plans.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plangate/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PlanGate — terminal-native plan-review loop

Batch the decisions into a reviewable plan file instead of forcing the user through one-by-one chat. The user reviews in vim; their :w is the signal; you resolve and revise; no code until it's agreed. Full background & prior art: see the repo README.

Review markers (the contract). Everything the user reviews is markdown blockquotes:

> Q: — a question / decision / anything needing the user's input. Whenever you write a > Q: line, put an empty > A: line directly under it so the user jumps in and types the answer with no marker typing (their vim has ]a to jump to the next empty > A: and start typing).
> A: — the answer. The user fills the empty slot; you fill it when replying to a > Q: the user raised.
An open item = an empty > A: slot (^\s*> A:\s*$), plus any > Q: the user added with no > A: under it. The loop is done when every > Q: has a non-empty > A: beneath it.
Blockquotes keep the plan valid markdown (renders fine in Obsidian/GitHub) and — with the bundled vim reading setup (see README) — highlight > Q: vs > A:, with ]q/[q to page between open questions.

Helper scripts live beside this file:

open-plan.sh <file> — open/focus the plan in a right-side vim pane (its own pane; never hijacks the user's working vim).
wait-save.sh <file> [max_s] — block until the user saves; run it in the BACKGROUND so their :w re-invokes you.
nudge-reload.sh — after you edit the plan, refresh the user's vim (:checktime + autoread) to show your > A: answers.
prune-plans.sh <plans-dir> [days] — delete plan files untouched for N days (default 7). Run it once per plan, at step 2.

When to fire

2+ open decisions/tradeoffs, or multiple implementation steps → propose the loop.
One simple/single-answer question → just answer, no plan.
If the user says "just answer" / "skip the plan" → drop the loop for that task.

Loop

Scope it. Feature comes from the /plangate <description> argument if given, else infer it from the conversation and confirm your one-line summary before writing.

Read the full file on GitHub · 110 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

2mo ago First seen · 110 lines · 131 tokens per session scan A 0ae009b55e2e

Subscribe to this mod's changes

plangate is a skill published in the GitHub repository ParthGanatra/agent-skills (7 stars, last pushed 3mo ago), licensed MIT. It adds 131 tokens to every session and 1,898 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-31.

Claude Code Planning agent-skills ai claude claude-skill claude-skills

plangate next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
plangateParthGanatra/agent-skills	Skill	7	3mo ago	MIT	A	131	Claude Code, Codex
declaudingoaustegard/claude-skills	Skill	158	yesterday	MIT	A	223	Claude Code, Codex
generative-thinkingoaustegard/claude-skills	Skill	158	yesterday	MIT	A	152	Claude Code, Codex
swarming-to-greenoaustegard/claude-skills	Skill	158	yesterday	MIT	A	220	Claude Code
developing-preactoaustegard/claude-skills	Skill	158	yesterday	MIT	A	76	Claude Code, Codex
orchestrating-chat-agentsoaustegard/claude-skills	Skill	158	yesterday	MIT	A	104	Claude Code, Codex
compiling-wgsloaustegard/claude-skills	Skill	158	yesterday	MIT	A	206	Claude Code, Codex