iso-plan

iso-plan is a skill for Claude Code from IsaiaScope/ai. It costs 97 tokens per session (2,685 once invoked), scanned A, original, MIT.

A planning workflow that turns a rough idea into a written implementation plan. It moves through brainstorming, critical questioning, optional prototyping, and plan writing without implementing the work.

In plain words
What is it for?
Use it to explore an idea, test uncertain parts with a prototype when needed, produce a plan file, and record the plan in the repository's tracking system when working inside a repository.
Why use it?
It separates deciding what to build from changing the code, so requirements and risks can be examined before implementation begins.

Skill for Claude Code

Written for Claude Code: SessionEnd hook event.

Good fit Use it to explore an idea, test uncertain parts with a prototype when needed, produce a plan file, and record the plan in the repository's tracking system when working inside a repository.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/isaiascope/ai/iso-plan
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 IsaiaScope/ai --skill iso-plan
Clone the repo
git clone --depth 1 https://github.com/IsaiaScope/ai

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.

agentmods badge for iso-plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/isaiascope/ai/iso-plan/github.svg)](https://agentmods.dev/skills/isaiascope/ai/iso-plan)
Your own site
<a href="https://agentmods.dev/skills/isaiascope/ai/iso-plan"><img src="https://agentmods.dev/badge/skills/isaiascope/ai/iso-plan/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.

agentmods 80×15 button for iso-plan

Your own site · 80×15
<a href="https://agentmods.dev/skills/isaiascope/ai/iso-plan"><img src="https://agentmods.dev/badge/skills/isaiascope/ai/iso-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,685 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00097 $0.02685
Opus 5 $0.00048 $0.01342
Sonnet 5 $0.00019 $0.00537
Haiku 4.5 $0.00010 $0.00268

Measured 4d ago against content hash ffab13b07a3e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

iso-plan 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 4d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/plan.sh, scripts/plan.test.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.

skills/iso-plan/SKILL.md · 224 lines

How it starts

The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.

iso-plan

Take a raw idea and turn it into a written implementation plan by running four skills in order. The only artefact is the plan file — nothing is implemented and nothing is committed. The one piece of state it writes is the Multica ticket that tracks the plan, and only inside a repo. When the plan is written, tell the user where it lives.

Pipeline

brainstorming   → superpowers:brainstorming   (always)
grilling        → grill-with-docs | grill-me  (always — gated, see step 2)
prototype       → prototype                   (only when needed — agent's call)
writing         → superpowers:writing-plans   (always)

Steps

Run each via the Skill tool, in order. The skills share this conversation's context, so the design carries forward automatically — there is no handoff artifact between steps.

If the user passed an argument, it is the seed idea — hand it to brainstorming. If not, brainstorming starts from the conversation so far.

  1. brainstorming — invoke superpowers:brainstorming. Explore intent, requirements, and shape of the idea.

  2. grilling (gated) — which grill skill runs depends on where you are. Resolve it with one check, before invoking anything:

scripts/plan.sh gate     # -> no-repo | setup-done | setup-missing
state action
no-repo invoke grill-me — no domain model to grill against
repo + setup-done invoke grill-with-docs — stress-test against CONTEXT.md + ADRs, sharpen terminology, update docs inline
repo + setup-missing halt the chain

docs/agents/domain.md is written by setup-matt-pocock-skills; its absence means grill-with-docs has no configured domain-doc layout to read, so it would invent one. Do not fall back to grill-me inside a repo, and do not run setup yourself — the user picks the issue tracker and label vocabulary. Print this and stop:

iso-plan: halted — repo not set up for grill-with-docs.
Run /setup-matt-pocock-skills first, then re-run /iso-plan.

Read the full file on GitHub · 224 lines

Files

What ships with it

3 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.

  1. 4d ago Changed · +5 lines ffab13b07a3e
  2. 9d ago First seen · 219 lines · 97 tokens per session scan A 191c8bc1c3dc

Subscribe to this mod's changes

iso-plan is a skill published in the GitHub repository IsaiaScope/ai (2 stars, last pushed 5d ago), licensed MIT. It adds 97 tokens to every session and 2,685 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories

agent-architecture-planner

Use when designing an autonomous agent, planning agent architecture, building a scheduled automation, or creating a Claude Code agent workflow. Triggers: 'design an agent', 'build an automation', 'agent architecture', 'automate this workflow', 'create a scheduled agent', 'shell script agent'.

majiayu000/claude-skill-registry · 64 tokens

remotion-upgrade

Upgrade Remotion, and related packages.

guanyang/open-agent-hub · 12 tokens

agent-curator

Deep curation of a single agent definition through structured human conversation. Coordinates knowledge research, persona refinement, tooling optimization, and instruction quality improvement. One agent at a time, with due care.

majiayu000/claude-skill-registry · 39 tokens

remotion-docs

Search and fetch Remotion documentation pages.

guanyang/open-agent-hub · 12 tokens

agent-browser

Agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling forms and auth, waiting for content, running multiple…

majiayu000/claude-skill-registry · 112 tokens

agent-builder

Build custom AI agents in Claude Code from a user's problem statement. This skill analyzes the user's use case, asks smart clarifying questions, researches the internet for similar agents (GitHub repos, blogs, Claude Code community patterns), and then architects and builds production-ready Claude Code agents …

majiayu000/claude-skill-registry · 199 tokens