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 5.5 | $0.00013 | $0.00214 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 (619 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 534 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 2026-08-30.
Other skills, from other repositories
temp-file-python-analysis
Inline Python in shell scripts has quoting issues.
Context Hygiene & Session Management
Monitors conversation complexity and manages session boundaries. Proactively secures state and memory before advising the user to split work across separate chat sessions, preventing context bloat.
material-organizer
Organize only the materials the user has already provided or explicitly pointed to. The job is to make messy inputs easier to scan, reuse, archive, or continue from later while preserving source traceability.
slacrawl
Archive and search Slack workspace messages, threads, and channels via the slacrawl CLI. Supports API sync, Slack export ZIP import, local desktop cache import, and full-text search.
obsidian
Read, search, and create notes in the Obsidian vault.
gmail-trigger
Beta. Act on new Gmail as it arrives: get pinged only for urgent mail, digest newsletters, forward invoices — any standing instruction, across one or several accounts.