A planning tool that turns a short brief into a written PLAN.md. The plan breaks work into tasks, shows which tasks depend on others, and defines how success will be checked.

Use it to create an executable plan from a brief, existing specification, or research notes. It can organize tasks into dependency waves and record success criteria.

It gives an unclear request a concrete sequence of work instead of leaving decisions and dependencies scattered across conversation notes. It can be used for software, books, campaigns, design work, or research.

ijfw-plan — Skill for Claude Code by FerroxLabs/ijfw

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 FerroxLabs/ijfw --skill ijfw-plan

Clone the repo

git clone --depth 1 https://github.com/FerroxLabs/ijfw

Made for: Claude Code.

Or install ijfw, the plugin that ships this one along with the rest of its 34 skills, 22 commands, 37 agents, 6 hooks.

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/ferroxlabs/ijfw/ijfw-plan/github.svg)](https://agentmods.dev/skills/ferroxlabs/ijfw/ijfw-plan)

Your own site

<a href="https://agentmods.dev/skills/ferroxlabs/ijfw/ijfw-plan"><img src="https://agentmods.dev/badge/skills/ferroxlabs/ijfw/ijfw-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.

Your own site · 80×15

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

Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,355 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00095	$0.02355
Opus 5.5	$0.00038	$0.00942
Sonnet 5.5	$0.00019	$0.00471
Haiku 4.5	$0.00010	$0.00235

Measured 1mo ago against content hash 2d74a2545a7e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ijfw-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 1mo 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.

claude/skills/ijfw-plan/SKILL.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

IJFW Plan — domain-agnostic plan authoring

You are the orchestrator-facing trigger that turns a brief (and optionally a SPEC.md / research notes) into an executable PLAN.md. Plan output is the same shape across domains: software slice, book chapter, marketing campaign, design system release, research milestone. The deliverables differ; the structure doesn't.

This skill is the body for the /ijfw-plan slash command. Both paths land here. Slash invocation may pass [brief description] as $1.

When to fire

User explicitly asks: "plan this", "plan it", "make a plan", "let's plan", "draft a plan", "break this down".
/ijfw-plan slash command is invoked.
ijfw-workflow Deep path enters the Plan gate after Discovery + Research.
ijfw-spec-phase has emitted SPEC.md and the user wants HOW next.

If .ijfw/memory/brief.md is missing AND no SPEC.md exists for the active slice, ask one clarifying question first: What are we planning? (one sentence). Never guess.

Inputs (read in order, skip missing)

.ijfw/memory/brief.md — original ask + success criteria.
.ijfw/memory/research.md — anything Discovery / Research surfaced.
.planning/<milestone>/<phase>/SPEC.md — locked acceptance criteria.
.planning/<milestone>/<phase>/CONTEXT.md — decisions resolved in discuss.
.planning/ROADMAP.md — where this slice sits in the bigger arc.
.planning/PROJECT.md — non-negotiables.

Detect domain from brief language and project layout:

Software: package.json, pyproject.toml, Cargo.toml, source dirs.
Book / chapter: manuscript/, chapters/, outline.md, prose-heavy brief.
Campaign / launch: campaign/, assets/, calendar / channel language.
Design system: tokens/, components/, design-ops language.
Research: notes/, papers/, "review the literature" framing.

Domain choice changes vocabulary, NOT the output shape.

Output location

If a phase is active (.ijfw/state/active-milestone + .ijfw/state/active-phase both exist), write to .planning/<milestone>/<phase>/PLAN.md and also mirror the task list to .ijfw/memory/plan.md for the runtime gate to read.

Read the full file on GitHub · 220 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.

1mo ago First seen · 220 lines · 95 tokens per session scan A 2d74a2545a7e

Subscribe to this mod's changes

ijfw-plan is a skill published in the GitHub repository FerroxLabs/ijfw (214 stars, last pushed 6d ago), licensed MIT. It adds 95 tokens to every session and 2,355 once invoked, about $0.0004 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 2026-09-05.

Claude Code Planning Project management ai-agents ai-coding codex cursor developer-tools

ijfw-plan

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

IJFW Plan — domain-agnostic plan authoring

When to fire

Inputs (read in order, skip missing)

Output location

What this file has done since we first saw it

Other skills, from other repositories

issue-creation

systemic-issue-triage

jira

revert

standup

status