Borrowing it
Nothing to install: this file belongs to serbanghita/plan-critique-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/serbanghita/plan-critique-skills/main/.gemini/skills/plan-create/SKILL.mdgit clone --depth 1 https://github.com/serbanghita/plan-critique-skillsWrote 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.
[](https://agentmods.dev/skills/serbanghita/plan-critique-skills/plan-create)<a href="https://agentmods.dev/skills/serbanghita/plan-critique-skills/plan-create"><img src="https://agentmods.dev/badge/skills/serbanghita/plan-critique-skills/plan-create/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.
<a href="https://agentmods.dev/skills/serbanghita/plan-critique-skills/plan-create"><img src="https://agentmods.dev/badge/skills/serbanghita/plan-critique-skills/plan-create.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00013 | $0.01004 |
| Opus 5 | $0.00006 | $0.00502 |
| Sonnet 5 | $0.00003 | $0.00201 |
| Haiku 4.5 | $0.00001 | $0.00100 |
Grade A, and why
plan-create 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 3d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- create — 98% identical, 19 lines differ
What it actually says
You are creating a new plan folder for the user.
Fixed rules:
Read the working agreement at working-agreement.md before step 1 and follow it for
the whole run. If that path does not resolve, look for working-agreement.md in the project root, then in
.gemini/. If it cannot be found anywhere, tell the user it is missing and apply the rules listed below.
These rules bind this phase and override any step below that conflicts with them:
- Ask clarifying questions up front when the request is ambiguous. Do not guess the plan name, the plans folder, or what the user means. Guessing here produces the wrong plan.
- Do not write, edit, or refactor any project code during this phase. This phase produces a plan folder and a
plan.mdand nothing else. - The plan is not finished until it lists its affected files and how success will be verified. The template carries both sections, so do not remove them when filling it in.
- Be brief. No filler, no preamble, no restating the request. No emojis, no em dashes, no decorative icons.
To do this, follow these steps precisely:
- Display the following banner before doing anything else:
+-------------------------------------------------+ | Plan Critique v2.6.1 - Creating new plan | +-------------------------------------------------+ - Read
.gemini/plan-critique-config.jsonand getplansFolderpath from settings. If that file does not exist, read.claude/plan-critique-config.jsoninstead, so a project already using the Claude Code plugin keeps the same plans folder. If neither file exists orplansFolderis not set or is an empty string:- Ask the user: "Where would you like to store your plans? Provide a folder path (default
.planning):". By default, the user should be presented with the option.planning. - Save the path as
plansFolderin.gemini/plan-critique-config.json - Create the folder if it doesn't exist
- Create an
archived/subfolder inside it
- Ask the user: "Where would you like to store your plans? Provide a folder path (default
- Determine the plan name:
- If a name was passed as an argument, the text in
$ARGUMENTSis the plan name. Use it directly. - Otherwise, ask the user directly, do not offer predefined options like "New Feature" or "Bug Fix" because the plan name must be unique: "Enter a name for this plan:" The plan name must have at least 3 characters. If it is empty or shorter, respond with "Plan name must be at least 3 characters." and ask the user to enter one.
- If a name was passed as an argument, the text in
- Generate a slug from the plan name:
- Convert to lowercase
- Replace spaces with hyphens
- Remove characters that are not alphanumeric or hyphens
- Trim to max 50 characters
- Example: "Add User Authentication" becomes
add-user-authentication
- Check if
[plansFolder]/[slug]/already exists. If it does: Respond with "A plan with this name already exists at[plansFolder]/[slug]/. Choose a different name." Ask for a new name and repeat from step 4. - Create directory
[plansFolder]/[slug]/ - Link this session to the new plan:
- Get the session process ID by running:
echo $PPID - Create the sessions directory if needed:
[plansFolder]/.sessions/ - Write the slug to
[plansFolder]/.sessions/[PID](plain text, just the slug)
- Get the session process ID by running:
- Create the plan template at
[plansFolder]/[slug]/plan.mdusing the template in plan-template.md. - Respond with confirmation:
Created new plan: [plansFolder]/[slug]/ Edit your plan at: [plansFolder]/[slug]/plan.md When ready, run `/plan-critique` to review your plan.
Notes:
- The slug must be filesystem-safe (no special characters)
- Keep the original plan name with proper casing in the H1 heading of plan.md
- Only create plan.md initially (critique.md is created by
/plan:critique) - Always use
plansFolderfrom settings as the base directory
What ships with it
1 file 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.
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.
- 3d ago Changed 4b732820f880
- 11d ago First seen · 78 lines · 13 tokens per session scan A a33878c81358
plan-create is a skill published in the GitHub repository serbanghita/plan-critique-skills (13 stars, last pushed 3d ago), licensed MIT. It adds 13 tokens to every session and 1,004 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.
Other skills, from other repositories
review-responder
Use when receiving feedback on code you implemented, responding to reviewer comments, deciding which review suggestions to implement, or pushing back on incorrect review feedback.
pr-sweep
Use when you want to sweep all open pull requests across all repos, triage their status, run code reviews on unreviewed PRs, merge what's ready, fix quick blockers, and produce a full status report. Trigger when the user says "check my PRs", "close out open PRs", "what's the status of my PRs", "sweep my PRs", "PR…
rubber-ducky
Use when you've planned a non-trivial change and are about to implement it, finished a complex or multi-file piece of work, just wrote tests, or are stuck on repeated failures — and any time the user says "rubber duck this", "rubber ducky", "get a second opinion", "sanity-check my plan", "poke holes in this", "what am…
open-pr
Use when wrapping up a development task and getting a PR ready — runs local tests, creates a PR (if one doesn't exist) with a structured description template, conducts a code review via the review skill, and checks CI status with quick fixes. Trigger when the user says they're done with a feature, want to open a PR…
review
Use when user invokes /review to review code changes. Also triggers on "review my code", "check this PR", "look at my changes". Accepts a PR number (e.g. /review 123), a path filter (e.g. /review src/auth/), or no argument (reviews current branch vs base). Produces structured per-file review with severity labels…
code-reviewer
Use when reviewing pull requests, analyzing code quality, identifying issues, or generating review checklists. Covers TypeScript, JavaScript, Python, Go, Swift, and Kotlin.