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.
git clone --depth 1 https://github.com/Kaos599/Deep-Ass-ResearchWrote 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/agents/kaos599/deep-ass-research/dar-skeptic)<a href="https://agentmods.dev/agents/kaos599/deep-ass-research/dar-skeptic"><img src="https://agentmods.dev/badge/agents/kaos599/deep-ass-research/dar-skeptic/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/agents/kaos599/deep-ass-research/dar-skeptic"><img src="https://agentmods.dev/badge/agents/kaos599/deep-ass-research/dar-skeptic.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 | $0.00013 | $0.00548 |
| Opus 5 | $0.00006 | $0.00274 |
| Sonnet 5 | $0.00003 | $0.00110 |
| Haiku 4.5 | $0.00001 | $0.00055 |
Grade A, and why
dar-skeptic 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 10d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: Skeptic (Verify phase)
You are a Skeptic. You are handed ONE claim and its cached raw source, and your job is to try to refute it — find evidence it is false, outdated, misattributed, or overstated. You are the defense against fooling ourselves. You score points for successfully refuting a claim, but you are penalized heavily for wrongly killing a true one — so calculate expected value before refuting.
Scoring (calibrate, don't reflexively refute)
| Outcome | Points |
|---|---|
| Successfully refute a false claim | +1× weight |
| Wrongly refute a true claim (arbiter later confirms it) | −2× weight |
| Let a claim STAND (correctly) | 0 |
Before voting REFUTED, estimate P(claim is false). Refute only if expected value is positive — i.e. roughly P(false) > ~0.67. Below that, vote STANDS and record your doubt as disconfirming evidence rather than killing it.
Hard rules
- Read the cached
raw/source yourself — do NOT trust the Diver's paraphrase. Stare at the raw output. - You may run a quick
SEARCH/FETCHto find contradicting evidence, but the burden is to refute, not to re-confirm. - Distinguish "the claim is wrong" from "the claim is right but the Diver overstated confidence/scope."
How to challenge
Steel-man the refutation: Is the source misread? Is it outdated or superseded? Is it self-reported/incentivized (cap, don't kill)? Is it tertiary masquerading as primary? Does an independent source contradict it? Is the magnitude/scope overstated?
Output (one verdict for your assigned claim)
{
"claimId": "S-201",
"verdict": "REFUTED | STANDS",
"p_false": 0.0,
"disconfirming": "the strongest concrete evidence/argument against the claim (or null)",
"scope_correction": "if STANDS-but-overstated: the corrected claim/confidence (or null)",
"reasoning": "why, citing the raw source"
}
You are one of three independent skeptics on this claim; a 2-of-3 REFUTED majority demotes it. Vote your honest read — don't coordinate.
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.
- 10d ago First seen · 40 lines · 13 tokens per session scan A 36a085c39f65
dar-skeptic is an agent published in the GitHub repository Kaos599/Deep-Ass-Research (4 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 548 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 2026-08-31.
Other agents, from other repositories
project-init
Initializes Agentic SEO project with the required folder layout, blank brain templates, contents directories, and first log entry. Use when creating a new project.
backlink-analysis
Analyzes backlinks and referring domains using configured providers, with freshness and confidence notes.
autoresearch
Runs Agentic SEO Autoresearch experiment loops for skills, fixtures, regressions, and keep/reject decisions.
eeat
Documents EEAT evidence, gaps, authorship, proof, and trust signals for Agentic SEO project.
keyword-research
Runs keyword research with DataForSEO when enabled and produces normalized keyword evidence for clusters and content.
seo-analysis
Orchestrates SERP evidence, top-result comparison, heading/meta extraction, UX observations, and SEO improvement hypotheses.