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/commands/kaos599/deep-ass-research/dar)<a href="https://agentmods.dev/commands/kaos599/deep-ass-research/dar"><img src="https://agentmods.dev/badge/commands/kaos599/deep-ass-research/dar/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/commands/kaos599/deep-ass-research/dar"><img src="https://agentmods.dev/badge/commands/kaos599/deep-ass-research/dar.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 | $0.00030 | $0.00207 |
| Opus 5.5 | $0.00012 | $0.00083 |
| Sonnet 5.5 | $0.00006 | $0.00041 |
| Haiku 4.5 | $0.00003 | $0.00021 |
Grade A, and why
dar 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 2mo 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.
What it actually says
Run the deep-ass-research skill on: $ARGUMENTS
Follow core/orchestration.md exactly. Start with the preflight and the Decompose & Charter step — ask me the clarifying questions (scope, the decision this feeds, recency, seed sources) before spending search budget. Use the registered DAR role subagents (dar-scout, dar-deep-diver, dar-skeptic, dar-arbiter, dar-librarian, dar-synthesizer, dar-relevance-monitor) for the phases, in parallel where independent. Honor the budget discipline in core/orchestration.md. At the end, show me the Map of Content, the per-success-criterion status, and the open questions, plus the vault path.
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.
- 2mo ago First seen · 9 lines · 30 tokens per session scan A 08b801115bca
dar is a command published in the GitHub repository Kaos599/Deep-Ass-Research (4 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 207 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
qec-reproduce
Look up and execute reference manual Appendix D (D.1 through D.6) reproduction workflows.
qec-code-inspect
Inspect quantum code family properties, parity check matrices, transversals, and distance bounds.
qec-dem
Inspect and parse Detector Error Models (DEM), Stim circuit definitions, and parallel fault collapse rules.
qec-wilson
Calculate Wilson 95% score confidence intervals and comparative statistical tables for Monte Carlo LER data.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.