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.
npx skills add human-avatar/skills-for-humanity --skill s4h-investigation-claim-decompositiongit clone --depth 1 https://github.com/human-avatar/skills-for-humanityWrote 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/human-avatar/skills-for-humanity/s4h-investigation-claim-decomposition)<a href="https://agentmods.dev/skills/human-avatar/skills-for-humanity/s4h-investigation-claim-decomposition"><img src="https://agentmods.dev/badge/skills/human-avatar/skills-for-humanity/s4h-investigation-claim-decomposition/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/human-avatar/skills-for-humanity/s4h-investigation-claim-decomposition"><img src="https://agentmods.dev/badge/skills/human-avatar/skills-for-humanity/s4h-investigation-claim-decomposition.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.01768 |
| Opus 5 | $0.00048 | $0.00884 |
| Sonnet 5 | $0.00019 | $0.00354 |
| Haiku 4.5 | $0.00010 | $0.00177 |
Grade A, and why
s4h-investigation-claim-decomposition 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investigation: Claim Decomposition
Complex claims are bundles. "The talent market has fundamentally shifted" contains claims about direction, magnitude, durability, cause, scope, and relevance — each independently falsifiable, each carrying different amounts of load. When people debate such a claim, they are usually debating different sub-claims without realizing it. Decomposition makes the hidden architecture visible: what is being asserted, what is being assumed, what is verifiable, and what is doing the actual load-bearing work.
Your Process
Step 1: State the Master Claim Write out the claim in its current form. If it was stated imprecisely, note that — but trace it faithfully. Do not pre-interpret; decompose what was actually asserted.
Framing check: Confirm the specific claim before continuing. State what you've identified — the actual claim being decomposed and its apparent domain (factual, causal, normative, etc.) — in one sentence, then use AskUserQuestion:
- Question: "I'm reading this as: [your one-sentence framing of the claim and its domain]. Is that right?"
- Header: "Framing"
- Options:
- Yes — proceed — framing is correct
- Adjust — one element is off; user will correct it before you continue
- Reframe — different claim than read; incorporate the correction before proceeding
Step 2: Decompose into Atomic Sub-Claims Break the master claim into the smallest independently assessable statements. Each sub-claim should be:
- A single, specific assertion
- Independently falsifiable (you could in principle evaluate it separately from the others)
- Not a combination of two ideas that are themselves separable
Common decomposition dimensions:
- Factual claims — assertions about what is true right now
- Causal claims — assertions about what causes what
- Trend claims — assertions about direction, rate, or duration of change
- Comparative claims — assertions about relative magnitude (more than, better than)
- Definitional claims — assertions about what a term means or what counts as X
- Normative claims — assertions about what should be done or what is good
- Scope claims — how broadly the main claim applies (always, usually, in some contexts)
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.
- 9d ago First seen · 143 lines · 95 tokens per session scan A a7f1a5ebd376
s4h-investigation-claim-decomposition is a skill published in the GitHub repository human-avatar/skills-for-humanity (223 stars, last pushed 1mo ago), licensed MIT. It adds 95 tokens to every session and 1,768 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 2026-09-03.
Other skills, from other repositories
decision-making-under-pressure
Provides practical habits for making better decisions faster -- reframing problems before solving them, knowing when to stop deliberating, balancing intuition with analysis, resisting 'just this once' compromises, and breaking overthinking cycles. Use when facing a high-stakes choice with incomplete data, sensing that…
flow-state
Optimizes individual and team productivity using Csikszentmihalyi's flow state framework, covering the conditions for flow (clear goals, immediate feedback, challenge-skill balance), the four-stage flow cycle, and organizational flow design. Use when auditing personal or team focus time, diagnosing productivity loss…
stoic-right-action
Applies Stoic ethics of right action to entrepreneurial decision-making, covering the four cardinal virtues (courage, justice, temperance, wisdom), ethical leadership under pressure, and the discipline of choosing the harder right over the easier wrong. Use when facing ethical dilemmas in business, building a…
bakeoff
Turn one decision into a judged tournament of solutions, then pick the best. Given a problem, design choice, or a suggestion you want cross-verified, it generates diverse candidate solutions, auto-derives the evaluation dimensions for THAT problem (so you don't have to know what to score on), judges every candidate…
balanced-scorecard
Translate strategy into metrics across Financial, Customer, Internal Process, and Learning & Growth perspectives.
customer-journey-map
Visualize every touchpoint a customer has with a product or service — stages, actions, emotions, pain points, opportunities.