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 Kaos599/Deep-Ass-Research --skill deep-ass-researchgit 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/skills/kaos599/deep-ass-research/deep-ass-research)<a href="https://agentmods.dev/skills/kaos599/deep-ass-research/deep-ass-research"><img src="https://agentmods.dev/badge/skills/kaos599/deep-ass-research/deep-ass-research/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/kaos599/deep-ass-research/deep-ass-research"><img src="https://agentmods.dev/badge/skills/kaos599/deep-ass-research/deep-ass-research.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 | $0.00115 | $0.00824 |
| Opus 5.5 | $0.00046 | $0.00330 |
| Sonnet 5.5 | $0.00023 | $0.00165 |
| Haiku 4.5 | $0.00012 | $0.00082 |
Grade A, and why
deep-ass-research 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.
How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Ass Research (DAR) — Claude Code adapter
This is the Claude Code entry point for the portable DAR framework. The methodology is host-agnostic and lives in core/; this file just binds DAR's capability verbs to Claude Code's tools and tells you how to spawn the roles.
How to run
- Read
core/orchestration.mdand follow it exactly. It is the runbook (preflight → charter → breadth → gate → depth → drift guard → verify → synthesize → deliver). Read its referenced files as needed:core/capabilities.md,core/methodology.md,core/vault-layout.md,core/note-schemas.md,core/provenance.md, and the chosencore/modes/<mode>.md. - Spawn sub-agents with the Task / Agent tool (
subagent_type: general-purpose). For each role, readcore/roles/<role>.mdand paste its full content as the sub-agent prompt, then append a## Taskblock with the thread/claim context and the absolute vault path. (This mirrors thebug-hunt-reviewskill's dispatch pattern.) Run independent sub-agents in parallel by issuing multiple Task calls in one message. - Track progress in the vault files
_progress.mdand_open-threads.md(source of truth). You MAY also mirror_progress.mdinto TodoWrite for visibility.
Capability bindings (Claude Code)
| Verb | Binding |
|---|---|
WRITE_FILE |
Write / Edit |
ASK_USER |
AskUserQuestion |
SPAWN_SUBAGENT |
Task / Agent tool (general-purpose), parallel via multiple calls |
SEARCH |
Tavily / Exa MCP if present, else built-in WebSearch |
FETCH |
Tavily extract / Exa fetch if present, else built-in WebFetch |
BROWSE |
TinyFish MCP (run_web_automation) |
READ_DOCS |
Context7 + Ref MCP, else WebSearch+WebFetch on official docs |
Record the actual bindings (and any degraded verbs) in _session.md during preflight.
Optional acceleration (Workflow tool)
For determinism, resumability, and budget control, the Depth → Drift → Verify → Synthesize stretch MAY run via adapters/claude-code/dar-pipeline.workflow.js (native Workflow tool). If you use it: first read the role files in core/roles/ and the chosen core/modes/<mode>.md, then invoke the Workflow passing them in args (the script sandbox can't read files): args = {vault, mode, brief, threads, roles:{...}, playbook}. Otherwise just follow steps 3–5 of core/orchestration.md directly. Running DAR implies opting into multi-agent orchestration — announce the approach before launching.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 43 lines · 115 tokens per session scan A d01dc9489f72
deep-ass-research is a skill published in the GitHub repository Kaos599/Deep-Ass-Research (4 stars, last pushed 2mo ago), licensed MIT. It adds 115 tokens to every session and 824 once invoked, about $0.0005 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 skills, from other repositories
volt-firmware
Produce a complete firmware architecture spec for a described device — layer diagram, module responsibilities, HAL interface definitions, key state machines, RTOS decision. Use when asked to "design firmware architecture", "plan embedded firmware", "architect an IoT device", "how should I structure this firmware", or…
lens-metrics
Produce a complete metrics definition doc — metric name, formula, data source, segmentation, SQL or event tracking spec, and what good/bad looks like. Given a product area, outputs the full metrics spec. Use when asked to "define KPIs", "metrics framework", "what should we measure", "north star metric", or "instrument…
prism-ui
Implement a complete UI screen or feature from a Form visual spec. Use when asked to "build a page", "implement this screen", "build the frontend for this feature", or "create this UI".
proof-e2e
Build E2E test specs for critical user journeys — Playwright or Cypress, page objects, setup/teardown, CI config. Use when asked to "write E2E tests", "end-to-end testing", "browser tests", "UI tests", or "Playwright tests".
relay-deploy
Set up a complete deployment configuration — Dockerfile, deployment manifest, environment config, and rollback procedure. Use when asked about "deployment setup", "how do I deploy this", "deployment strategy", or "rollback plan".
vigil-alert
Write SLO-based alert rules with burn rate thresholds and paired runbooks. Outputs actual alert configs, not a strategy doc. Use when asked to "set up alerts", "create runbooks", "define SLOs", or "alerting strategy".