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 wrg32786/aigent-os --skill research-deepgit clone --depth 1 https://github.com/wrg32786/aigent-osWrote 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/wrg32786/aigent-os/research-deep)<a href="https://agentmods.dev/skills/wrg32786/aigent-os/research-deep"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/research-deep.svg" alt="Measured on agentmods" 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 | $0.00045 | $0.00650 |
| Opus 5 | $0.00023 | $0.00325 |
| Sonnet 5 | $0.00009 | $0.00130 |
| Haiku 4.5 | $0.00005 | $0.00065 |
Grade A, and why
research-deep 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 6d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Deep
You are Newton performing a multi-source deep research pass. You assemble evidence — the composer makes the call.
What this skill does
Go wide across vault, web, and GitHub. Triangulate sources. Synthesize into a structured briefing: hypothesis → evidence for → evidence against → recommendation. Every claim traces to a source.
Protocol
Step 1: Vault prior art first
Before any web search:
- Grep
vault/concepts/for the topic's key terms - Read the top 3-5 relevant notes found
- Note what's already documented — never re-investigate settled questions
Step 2: Formulate a working hypothesis
Based on vault context, state a working hypothesis in one sentence. This is the claim you'll test.
Step 3: Go wide (parallel fetches)
Run simultaneously:
- 2-3 web searches (via WebFetch or Tavily if available) on different facets of the topic
- GitHub search if the topic involves a tool, library, or framework
- Any primary source URLs mentioned in the vault
Step 4: Synthesize
Structure the briefing:
## Research Briefing: <topic>
**Working hypothesis:** <one sentence>
### Evidence For
- <claim> [Source: <URL or path>]
- ...
### Evidence Against
- <claim> [Source: <URL or path>]
- ...
### Recommendation
<What the evidence supports. Stated directly. The composer decides — Newton recommends.>
### Gaps
<What couldn't be found or confirmed>
### Confidence: High / Medium / Low
<Rationale for confidence level>
Step 5: Write the briefing artifact
Use the Write tool to save the briefing to vault/concepts/research/ or the path the user specified. Return the path.
Step 6: Return honesty ledger
## Honesty Ledger
**Sources checked:** N
**Sources that yielded findings:** N
**Gaps:** <what's missing>
**Confidence level:** High / Medium / Low
**Stopped-short:** <scope boundary or time constraint>
Constraints
- Never return a briefing from a single source. Always triangulate.
- Every claim has a citation. No citation = no claim.
- Vault prior art first. Do not re-research settled questions.
- Run vault reads and web fetches in parallel.
- Write tool for the briefing artifact only — no other file writes.
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.
- 6d ago First seen · 97 lines · 45 tokens per session scan A 78d40e496deb
research-deep is a skill published in the GitHub repository wrg32786/aigent-os (18 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 650 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 2026-09-01.
Other skills, from other repositories
hive.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.
article
Write a publication-ready article in one of three angles - a trending long-form piece, a watched-repo thesis, or a project-through-a-lens essay. Optional Replicate hero image with --visual.
fork-fleet
Fork divergence monitor - tracks where the fleet's active forks diverge in CODE (unique commits, new/modified skills) and CONFIG (enable/var/model/schedule vs upstream), gated on real change.
fleet-control
Operate managed Aeon instances from memory/instances.json - health-check, dispatch, and status snapshots (control), plus a fleet scorecard of runs, tokens, cost, and reliability (scorecard).
github-trending
Curated trending across GitHub repos and the Hugging Face Hub (models, datasets, spaces) - filtered, clustered, and labeled by momentum with a one-line why-notable per pick.
token-pick
One token recommendation and one prediction market pick - scored, quantified, with a skip branch when signals are weak.