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-evidence-auditgit 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-evidence-audit)<a href="https://agentmods.dev/skills/human-avatar/skills-for-humanity/s4h-investigation-evidence-audit"><img src="https://agentmods.dev/badge/skills/human-avatar/skills-for-humanity/s4h-investigation-evidence-audit/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-evidence-audit"><img src="https://agentmods.dev/badge/skills/human-avatar/skills-for-humanity/s4h-investigation-evidence-audit.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 | $0.00098 | $0.01811 |
| Opus 5 | $0.00049 | $0.00905 |
| Sonnet 5 | $0.00020 | $0.00362 |
| Haiku 4.5 | $0.00010 | $0.00181 |
Grade A, and why
s4h-investigation-evidence-audit 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investigation: Evidence Audit
Evidence is not a binary: there or not there. A study can exist and be worthless. Multiple sources can exist and all be downstream of the same flawed original. The question is never just "is there evidence?" but "what kind, how strong, and what's missing?" A structured evidence audit answers all three. It places the available evidence in a hierarchy, evaluates it against the claim it's supposed to support, flags conflicts of interest, and explicitly names what should exist but doesn't.
Your Process
Step 1: State the Claim and Evidence Inventory Write out the claim you're evaluating. List all evidence currently offered in support — each study, data point, expert opinion, case, or example. Do not filter yet: capture the full inventory.
Framing check: Confirm the specific claim and evidence set before continuing. State what you've identified — the precise claim being evaluated and the body of evidence offered in its support — in one sentence, then use AskUserQuestion:
- Question: "I'm reading this as: [your one-sentence framing of the claim and its evidence]. 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 situation than read; incorporate the correction before proceeding
Step 2: Classify by Evidence Type Place each piece of evidence on the evidence hierarchy. Higher tiers provide stronger warrant for causal claims:
| Tier | Evidence Type | What It Establishes |
|---|---|---|
| 1 | Randomized controlled trial (RCT) | Causal relationship with controlled confounders |
| 2 | Pre-registered observational study | Association with reduced risk of p-hacking |
| 3 | Non-pre-registered observational / cohort study | Association; confounders possible |
| 4 | Systematic review / meta-analysis of weak studies | Aggregate of lower-quality evidence |
| 5 | Single survey or cross-sectional study | Snapshot correlation; causation not established |
| 6 | Expert opinion / consensus statement | Informed judgment; not independent evidence |
| 7 | Case study or qualitative report | Existence proof; not generalizable |
| 8 | Anecdote or testimonial | Personal experience; highly susceptible to bias |
| 9 | Assertion (no supporting evidence) | No evidential warrant |
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 · 145 lines · 98 tokens per session scan A d2f4affb0da9
s4h-investigation-evidence-audit is a skill published in the GitHub repository human-avatar/skills-for-humanity (223 stars, last pushed 1mo ago), licensed MIT. It adds 98 tokens to every session and 1,811 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.