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 yogsoth-ai/de-anthropocentric-research-engine --skill falsification-first-auditgit clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engineWrote 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/yogsoth-ai/de-anthropocentric-research-engine/falsification-first-audit)<a href="https://agentmods.dev/skills/yogsoth-ai/de-anthropocentric-research-engine/falsification-first-audit"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/de-anthropocentric-research-engine/falsification-first-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/yogsoth-ai/de-anthropocentric-research-engine/falsification-first-audit"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/de-anthropocentric-research-engine/falsification-first-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00071 | $0.00878 |
| Opus 5.5 | $0.00028 | $0.00351 |
| Sonnet 5.5 | $0.00014 | $0.00176 |
| Haiku 4.5 | $0.00007 | $0.00088 |
Grade A, and why
falsification-first-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 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.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
falsification-first-audit
Purpose
Convert a sharp claim into the cheapest decisive falsification program and return BROKEN, CORROBORATED, or UNFALSIFIABLE.
Input contract
mode_contracts:
sharp-claim: &falsification_input
required: [claim, scope, available_evidence]
optional: [mechanism, candidate_tests]
constraints: [claim_must_expose_observable_consequences_and_boundary_conditions]
truthseeking-debate: *falsification_input
truthseeking-red-team: *falsification_input
Execution protocol
Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.
- You MUST load skill
sharpen-falsifiable-claimto sharpen the claim. You MUST load skillsurface-assumptionsto expose its assumptions. - You MUST load skill
design-falsification-testto design the cheapest decisive falsification test. - You MUST load skill
execute-probeto execute the most informative probe. - You MUST load skill
classify-falsification-verdictto classify only the permitted truth-seeking verdict. If the claim depends on a structural mapping, consideraudit-structural-equivalence. If the test or oracle may be circular, consideraudit-validator-independence. If agreement among paths may not be independent, consideraudit-convergence-independence. If simplicity is carrying the claim, consideraudit-explanatory-compression. If survival is confined to an uncertain region, considermap-validity-envelope. Deviation: if no legitimate falsifier can be specified or reached, stop with UNFALSIFIABLE; do not substitute a resilience score.
Output contract
mode_contracts:
sharp-claim:
produces: [claim_falsifiability, refutation_condition, attacks_attempted, outcome_bucket, refutation_or_surviving_forbidden_content, honest_residue]
delta_fields: [findings, evidence_updates, hypothesis_updates, uncertainties, decisions]
truthseeking-debate:
produces: [most_falsifiable_form, committed_refuter, cross_examination_findings, attack_severity, outcome_bucket, refutation_or_forbidden_content]
delta_fields: [findings, evidence_updates, hypothesis_updates, uncertainties, decisions]
truthseeking-red-team:
produces: [claim_load_rank, assumption_classification, refutation_condition, refutation_attempt, outcome_bucket, framing_risk_brief]
delta_fields: [findings, evidence_updates, hypothesis_updates, uncertainties, decisions]
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 · 61 lines · 71 tokens per session scan A d6a8f0342d6e
falsification-first-audit is a skill published in the GitHub repository yogsoth-ai/de-anthropocentric-research-engine (505 stars, last pushed 4d ago), licensed Apache-2.0. It adds 71 tokens to every session and 878 once invoked, about $0.0003 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 2026-09-24.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…