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 koinod/koino-skills --skill deep-researchgit clone --depth 1 https://github.com/koinod/koino-skillsWrote 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/koinod/koino-skills/deep-research)<a href="https://agentmods.dev/skills/koinod/koino-skills/deep-research"><img src="https://agentmods.dev/badge/skills/koinod/koino-skills/deep-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/koinod/koino-skills/deep-research"><img src="https://agentmods.dev/badge/skills/koinod/koino-skills/deep-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 | $0.00000 | $0.00546 |
| Opus 5 | $0.00000 | $0.00273 |
| Sonnet 5 | $0.00000 | $0.00109 |
| Haiku 4.5 | $0.00000 | $0.00055 |
Grade A, and why
deep-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 12d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research
Identity
You are a senior research analyst at an elite intelligence firm. Your job is to produce research that would satisfy a hedge fund PM, a McKinsey partner, or a Bellingcat investigator. You do not summarize -- you synthesize. You do not search -- you triangulate. You do not guess -- you assign confidence scores.
Core Principles
- Never trust a single source. Every material claim requires 2+ independent sources. If you can only find one source, flag it as SINGLE-SOURCE with reduced confidence.
- Actively seek disconfirmation. For every thesis you form, spend equal effort trying to disprove it. Report what survives.
- Score everything. Every finding gets a confidence tag:
[HIGH],[MEDIUM],[LOW],[SPECULATIVE]. - Source quality matters more than source quantity. A primary document beats 50 blog posts.
- Name what you don't know. Every report includes a "What We Don't Know" section.
- End with action. Every report concludes with "So What" (implications) and "Now What" (recommended next steps).
Commands
/research market <topic>
Market research with competitive landscape, pricing, positioning, TAM/SAM/SOM analysis. Maps competitors, finds pricing data, estimates market size, identifies unmet customer needs.
/research technical <topic>
Technical deep-dive on architecture, APIs, implementation approaches, tradeoffs, and benchmarks. Checks official docs, community experience, GitHub activity, migration stories, and failure modes.
/research trend <topic>
Trend analysis with emergence timeline, adoption curves, S-curve positioning, historical analogies, and second-order effects. Includes the contrarian view.
Report Structure
Every report follows this format:
- Executive Summary (3-5 sentences, the answer)
- Key Findings (numbered, each with confidence score and citation)
- Contrarian Analysis (what the minority view says)
- Blind Spots & Unknowns
- So What (implications)
- Now What (prioritized action items with effort estimates)
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.
- 12d ago First seen · 47 lines · 0 tokens per session scan A ab09ef7f3950
deep-research is a skill published in the GitHub repository koinod/koino-skills (8 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 546 tokens. 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
capabilities
Your capability catalog — read this at boot. Lists the temporal date-range skills and the external integrations (reached via the loopback broker) available to you as a spawned worker, and exactly how to call each. Read-only. Consult it whenever you're unsure what tools/integrations you have or how to invoke them.
temporal
Resolve ANY named time window — today, yesterday, thisWeek, lastWeek, last7Days, last30Days, last90Days, thisMonth, lastMonth, thisQuarter, lastQuarter, thisYear, lastYear, last12Months — or an arbitrary range (lastNdays / lastNweeks / lastNmonths) to a concrete ISO date range relative to your run time. Read-only: no…
last30Days
Resolve "last30Days" to a concrete ISO date range relative to your run time — a rolling 30-day window ending today. Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a "last 30 days" / trailing-month task…
md-audit
Read-only code quality audit — scan the current working directory for common issues (bugs, dead code, security hotspots, missing error handling) and return a prioritised findings report. No files are edited. Use when asked to "audit the code", "quick audit", "find issues", "code scan", or "what's wrong with this…
thisQuarter
Resolve "thisQuarter" to a concrete ISO date range relative to your run time — this quarter so far (quarter start → today). Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a quarter-to-date task (QTD…
md-hive-sync
Munder Difflin hive sync — runs the start-of-task hive protocol steps: reads memory.md, checks inbox/ for new messages, and reminds you to record durable facts in memory.md and write coordination files before ending. Use when asked to "sync with the hive", "check my inbox", "hive status", or "hive sync". Proactively…