inversion

inversion is a skill for Claude Code from saadshahd/moo.md. It costs 24 tokens per session (470 once invoked), scanned A, original, MIT.

A problem-solving method that looks at what would guarantee failure and then reverses those actions into a plan. It is meant for goals that have already failed repeatedly.

In plain words
What is it for?
It examines earlier failed attempts, lists the actions that would make failure certain, and turns them into specific instructions to avoid.
Why use it?
It helps reveal the small habits, omissions, or decisions that keep derailing an approach.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the hope plugin — 20 skills, 1 command, 3 hooks shipped together

Good fit It examines earlier failed attempts, lists the actions that would make failure…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/saadshahd/moo.md/inversion
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 saadshahd/moo.md --skill inversion
Clone the repo
git clone --depth 1 https://github.com/saadshahd/moo.md

Made for: Claude Code.

Or install hope, the plugin that ships this one along with the rest of its 20 skills, 1 command, 3 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.

agentmods badge for inversion

README.md
[![agentmods](https://agentmods.dev/badge/skills/saadshahd/moo.md/inversion.svg)](https://agentmods.dev/skills/saadshahd/moo.md/inversion)
Your own site
<a href="https://agentmods.dev/skills/saadshahd/moo.md/inversion"><img src="https://agentmods.dev/badge/skills/saadshahd/moo.md/inversion.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 470 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 $0.00024 $0.00470
Opus 5 $0.00012 $0.00235
Sonnet 5 $0.00005 $0.00094
Haiku 4.5 $0.00002 $0.00047

Measured 7d ago against content hash 5cd7c89952ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

inversion 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 7d 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.

hope/skills/inversion/SKILL.md · 45 lines

What it actually says

Extract

From the conversation/context/user:

  • The goal as stated.
  • Its misses — the head-on attempts already made, and where each fell short.
  • The want — what the user is asking for in raising it: a new way at the goal, or something else.

Gate

Proceed only when: the goal has been tried head-on and missed more than once, and what's wanted is a new way at it — not the work done, not the damage owned.

Anything else, say which in one plain line — never invert anyway:

  • The goal hasn't been tried head-on yet → do the work; the head-on attempt governs what follows.
  • The failing is the execution, not the route → own it and fix it; the fixing governs what follows.
  • A list of what could go wrong is what's wanted → give the list plainly and proceed with the work — that list is itself the answer, nothing here owes it a negation.

Invert

Everything here runs inside this one turn — nothing waits on the user.

  1. Ask: what would make this goal certain to fail? List the fewest actions that guarantee it — things being done or skipped today count double. Prefer the certain small saboteur over the dramatic unlikely one.
  2. Negate each into one imperative line: a thing to do or a thing to stop.
  3. Cut any line that is a risk to watch rather than an action to take — a risk list is the inversion failing, not the route arriving.

The negated list is the route.

Output

Deliver the route — each line an imperative the user can act on — and stop there: nothing else rides along.

Then check whether anything still unresolved would change what gets built:

  • Nothing would → return to the work the inversion interrupted.
  • A line of the route rests on something already settled that the user does not hold → use explain skill.
  • A line's words admit two readings that would do different things → use clarify skill.

The inversion is spent once the route is out — anything further runs under the branch picked here, never as another inversion.

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. 7d ago First seen · 45 lines · 24 tokens per session scan A 5cd7c89952ba

Subscribe to this mod's changes

inversion is a skill published in the GitHub repository saadshahd/moo.md (34 stars, last pushed 21d ago), licensed MIT. It adds 24 tokens to every session and 470 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.

Related

Other skills, from other repositories

session-recap

Document Claude Code sessions by extracting knowledge into cross-referenced documentation. Triggers on "recap the session", "summarize the work", or after significant code changes.

sxhmilyoyo/sundayhao-plugins · 39 tokens

knowledge-bank-lookup

Delegates knowledge bank lookups to Explore subagents with reflections-first strategy that learns from past mistakes. Checks /reflections/ directory before documentation to extract documented failures to avoid and proven approaches to apply. Automatically triggers when user mentions services ([project-a], [project-b]…

sxhmilyoyo/sundayhao-plugins · 94 tokens

lark-openapi-explorer

A skill for finding and calling Lark APIs that are not already available through existing commands. An API is a defined way for software to request work from another service.

DropFan/claude-code-plugins · 76 tokens

kb-ingest

Ingest external sources into the knowledge bank through interactive study or quick filing. Two modes — Quick (summarize → file) and Study (theme-by-theme deep dive with online research and personal notes → multi-layer KB output → optional blog/slack synthesis). Triggers on "ingest this", "study this article", "add to…

sxhmilyoyo/sundayhao-plugins · 152 tokens

session-manager

Manage current Claude Code session metadata — set project, tags, and summary on session.md via Obsidian CLI. Use this skill whenever the user wants to tag, categorize, name, label, summarize, or organize the current session. Triggers on phrases like "tag this session", "this was about X", "mark this as", "session…

sxhmilyoyo/sundayhao-plugins · 132 tokens

lark-workflow-standup-report

A Feishu (Lark) workflow that combines calendar events with unfinished tasks into a daily schedule summary. Feishu is a workplace collaboration app with calendar and task features.

DropFan/claude-code-plugins · 53 tokens