plan-compass

plan-compass is a skill for Claude Code from softcane/human-state-skills. It costs 77 tokens per session (976 once invoked), scanned A, original, MIT.

A planning review that tests a proposed plan by asking one focused decision question at a time and checking which choices depend on others.

In plain words
What is it for?
Use it to review a plan, test whether it is workable, or walk through a decision step by step.
Why use it?
It helps reveal missing choices and dependencies without turning the review into a long, confusing questionnaire.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: installed under .agents/ (shared by several agents).

Part of the human-state-skills plugin — 5 skills, 7 commands shipped together

Good fit Use it to review a plan, test whether it is workable, or walk through a decision step by step.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/softcane/human-state-skills/plan-compass
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 softcane/human-state-skills --skill plan-compass
Clone the repo
git clone --depth 1 https://github.com/softcane/human-state-skills

Made for: Claude Code.

Or install human-state-skills, the plugin that ships this one along with the rest of its 5 skills, 7 commands.

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 plan-compass

README.md
[![agentmods](https://agentmods.dev/badge/skills/softcane/human-state-skills/plan-compass.svg)](https://agentmods.dev/skills/softcane/human-state-skills/plan-compass)
Your own site
<a href="https://agentmods.dev/skills/softcane/human-state-skills/plan-compass"><img src="https://agentmods.dev/badge/skills/softcane/human-state-skills/plan-compass.svg" alt="Measured on agentmods" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 976 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00077 $0.00976
Opus 5 $0.00039 $0.00488
Sonnet 5 $0.00015 $0.00195
Haiku 4.5 $0.00008 $0.00098

Measured 8d ago against content hash 4790f5943a83, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

plan-compass 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 8d 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.

.agents/skills/plan-compass/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan Compass

Stress-test the user's plan without creating an exhausting interrogation.

Core Loop

Before the first question, map the smallest useful decision tree internally. Separate discoverable facts from user-owned decisions. Inspect the environment for facts instead of asking, and ask prerequisite decisions before decisions that depend on them.

During the decision phase, ask exactly one decision question at a time.

Each question must include:

  1. The progress label.
  2. A compact state line.
  3. The question.
  4. Your recommended choice, which is also the default.
  5. Why this matters in one sentence.
  6. Two or three concrete answer choices.

Use this shape:

Decision 2 of 6: Data ownership

State: Locked: offline storage · Now: ownership · About 4 decisions remain

Question: Who owns the saved draft?

Recommendation/default: A — The user owns the draft.

Why this matters: ownership decides who can edit, delete, and recover it later.

Choices:
- A: User owns it.
- B: Team owns it.
- C: Project owns it.

Interaction Rules

  • Do not call the process "grilling" unless the user uses that word first.
  • Keep questions short and specific.
  • Do not ask broad open-ended questions unless unavoidable.
  • Do not ask multiple questions in one response.
  • Do not require the user to hold previous answers in memory.
  • Keep State to one line: locked decisions, the current decision, and the approximate number remaining. Summarize older decisions rather than letting the line grow.
  • Prefer examples over abstract categories.
  • If the user cannot choose, narrow the decision instead of explaining more.
  • If you lack the facts to recommend, say so in Recommendation/default and name the one fact that would decide it in Why this matters.
  • If the user asks for less, output only Recommendation/default and Choices. This is an explicit exception to the normal question format.
  • Keep tangents in a private parking lot. Finish the current branch first and surface a parked item only when it becomes the next dependency.
  • Make progress visible without praise or gamification.

Read the full file on GitHub · 130 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.

  1. 8d ago First seen · 130 lines · 77 tokens per session scan A 4790f5943a83

Subscribe to this mod's changes

plan-compass is a skill published in the GitHub repository softcane/human-state-skills (113 stars, last pushed 1mo ago), licensed MIT. It adds 77 tokens to every session and 976 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

tastemaker

Generate genuinely beautiful, on-brand UI instead of generic "AI slop" — use whenever the user asks to build, design, style, or improve a UI, landing page, dashboard, app screen, or component, whenever a PRD/spec needs a design pass before implementation, whenever the user pastes reference images/Pinterest/Dribbble…

codeswithroh/tastemaker · 202 tokens

fde

Keeps the engagement record for client work. Use when they name a client or stakeholder. Use when they debrief a meeting or paste notes. Use when they ask what was agreed. Use when they run a POC, change the client's codebase, prove it on their staging, go live, or need evals before a model acts. Use when they prep a…

suboss87/FDEOps · 125 tokens

kubernetes-skill

Prevent Kubernetes hallucinations by diagnosing and fixing failure modes: insecure workload defaults, resource starvation, network exposure, privilege sprawl, fragile rollouts, and API drift. Use when generating, reviewing, refactoring, or migrating manifests, Helm charts, Kustomize overlays, cluster policies, and…

LukasNiessen/kubernetes-skill · 89 tokens

image-to-psd

A skill that reconstructs images as editable, layered Photoshop files. It separates the repaired background, visual components, and text into layers instead of leaving the page as one flat image.

DSY-Xueai/image2editable · 75 tokens

img2mo-learn

Learn reusable 2D motion-generation knowledge from user-specified action resources with /img2mo-learn . Use when the user provides videos, extracted frame sequences, spritesheets, Spine assets, generated outputs, failed attempts, or reference motion folders and wants to summarize animation timing, pose beats, style…

WU-HAOTIAN34/2dimg2motion · 104 tokens

img2mo-std

Standardize a 2D animation baseline image with /img2mo-std xxx.png/pos. Use when preparing a character, creature, prop, or weapon baseline before motion generation, especially if the source image is too large, tightly cropped, lacks transparent action margin, has a white background, or later walk/attack/idle frames…

WU-HAOTIAN34/2dimg2motion · 87 tokens