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 winstonkoh87/Athena-Public --skill deep-research-loopgit clone --depth 1 https://github.com/winstonkoh87/Athena-PublicWrote 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/winstonkoh87/athena-public/deep-research-loop)<a href="https://agentmods.dev/skills/winstonkoh87/athena-public/deep-research-loop"><img src="https://agentmods.dev/badge/skills/winstonkoh87/athena-public/deep-research-loop/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/winstonkoh87/athena-public/deep-research-loop"><img src="https://agentmods.dev/badge/skills/winstonkoh87/athena-public/deep-research-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00032 | $0.00534 |
| Opus 5 | $0.00016 | $0.00267 |
| Sonnet 5 | $0.00006 | $0.00107 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade A, and why
Deep Research Loop 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 11d 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
🔬 Deep Research Loop
Philosophy: Go deep before going wide. One validated source > ten unverified claims.
1. The Prompt
Role: Senior Research Analyst.
Objective: Execute a structured multi-step research loop on the given topic. Produce a research brief with cited sources, cross-referenced claims, and confidence ratings.
2. Execution Workflow
STEP 1: SCOPE
└─ Define the research question in one sentence
└─ List 3-5 sub-questions that must be answered
STEP 2: GATHER (3+ Sources)
└─ Search for primary sources (official docs, papers, repos)
└─ Search for secondary sources (blogs, forums, discussions)
└─ Search for contrarian views (what disagrees?)
STEP 3: CROSS-REFERENCE
└─ For each claim: How many independent sources confirm it?
└─ Flag any claim with only 1 source as [UNVERIFIED]
STEP 4: SYNTHESIZE
└─ Produce the Research Brief (see Output Format below)
└─ Highlight conflicts between sources
STEP 5: CONFIDENCE RATING
└─ Rate overall confidence: HIGH / MEDIUM / LOW
└─ State what would change your assessment
3. Output Format
# Research Brief: [Topic]
## Key Findings
1. [Finding] — [Source] — Confidence: [H/M/L]
2. [Finding] — [Source] — Confidence: [H/M/L]
## Conflicts & Gaps
- [Source A] says X, but [Source B] says Y
## Recommendations
- [What to do with this information]
## Sources
1. [URL] — [Date accessed]
4. When to Use
- Before making any decision based on external information
- When the user says "find out everything about X"
- Before building something based on a technology you haven't used
skill #research #synthesis #fact-checking
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.
- 11d ago First seen · 73 lines · 32 tokens per session scan A 39fefeb41b17
Deep Research Loop is a skill published in the GitHub repository winstonkoh87/Athena-Public (587 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 534 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
imap-smtp-email
Read and send email via IMAP/SMTP. Check for new/unread messages, fetch content, search mailboxes, mark as read/unread, and send emails with attachments. Works with any IMAP/SMTP server including Gmail, Outlook, 163.com, vip.163.com, 126.com, vip.126.com, 188.com, and vip.188.com.
task_automation
Design effective automated workflows using scheduled tasks, prompt chaining, and delivery channels.
skill-factory
A workflow that examines completed session work and turns reusable patterns into Claude Code skills.
session-wrap
Use when wrapping up a session before ending. 4 parallel subagents detect doc updates, repeated patterns, learning points, and follow-ups, then a verifier deduplicates and presents choices. Triggers on /session-wrap, session wrap, session cleanup, end of session.
lark-cli
Use when the user wants to operate Lark or Feishu via the local lark-cli (@larksuite/cli), including install, app credentials, OAuth, readiness checks, and safe read/write boundaries.
opencli
Use when the user wants to use websites, browser login sessions, Electron apps, or external CLIs through a local OpenCLI setup, especially when setup guidance, readiness checks, and safe task execution are needed.