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 nanoAgentTeam/research-claw --skill conference-trackinggit clone --depth 1 https://github.com/nanoAgentTeam/research-clawWrote 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/nanoagentteam/research-claw/conference-tracking)<a href="https://agentmods.dev/skills/nanoagentteam/research-claw/conference-tracking"><img src="https://agentmods.dev/badge/skills/nanoagentteam/research-claw/conference-tracking/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/nanoagentteam/research-claw/conference-tracking"><img src="https://agentmods.dev/badge/skills/nanoagentteam/research-claw/conference-tracking.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 | $0.00061 | $0.00825 |
| Opus 5 | $0.00030 | $0.00413 |
| Sonnet 5 | $0.00012 | $0.00165 |
| Haiku 4.5 | $0.00006 | $0.00082 |
Grade A, and why
conference-tracking 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 9d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
[SKILL: CONFERENCE TRACKING PROTOCOL]
Activate when: user asks to track conference results, analyze acceptance trends, 会议跟踪, 会议录用, 录用结果分析, or wants submission advice based on conference patterns.
Execution Protocol
Step 1 — Check Memory for Previously Tracked Conferences
Call memory_nav(domain='job') to find previous tracking records under scope job:radar.conference.track.
Read recent entries (via memory_list then memory_get) to determine:
- Which conferences have already been tracked and when
- What was the analysis cutoff date for each conference
Step 2 — Discover New Conference Results
Search for conferences that have published new acceptance results since the last tracking.
Use web_search with queries like:
- "ICLR 2026 accepted papers announced"
- "NeurIPS 2025 accepted papers list" Focus only on conferences where results are NEW (not yet in memory).
Step 3 — Fetch the Official Full Paper List (mandatory)
For each conference with new results:
- Navigate to the official accepted papers page — e.g.:
- OpenReview:
openreview.net/group?id=ICLR.cc/YEAR/Conference - Virtual site:
conference.cc/virtual/YEAR/papers.html - Proceedings:
proceedings.mlr.press/vXXX/(ICML),papers.nips.cc/paper_files/paper/YEAR(NeurIPS)
- OpenReview:
- Use
web_fetchon the official URL to retrieve the full paper list. - Do NOT fall back to arxiv keyword search as a substitute for the official list. The goal is the complete, official acceptance record — not a keyword-filtered subset.
- If the page is too large, fetch the proceedings index or category listing pages.
Step 4 — Analyze Overall Trends from the Full List
From the complete paper list, identify:
- Top directions by paper count (cluster similar titles by topic)
- Emerging topics (strong presence this year vs. previous years)
- Methodology signals (theoretical vs empirical, large-scale vs efficient, benchmark types)
- Acceptance rate context (if available: total submissions vs acceptances)
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.
- 9d ago First seen · 69 lines · 61 tokens per session scan A d683e34dba24
conference-tracking is a skill published in the GitHub repository nanoAgentTeam/research-claw (293 stars, last pushed 3mo ago), licensed MIT. It adds 61 tokens to every session and 825 once invoked, about $0.0003 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
local-llm-tool
Local LLM execution tool for text generation and chat through Ollama or vLLM endpoints. Use when: running on-prem inference, calling a local GPU model, or summarizing with a self-hosted LLM.
sflo
Starts and manages SFLO factory runs through the configured runner. Use when the user explicitly asks to start, run, resume, list, kill, clean, or inspect an SFLO factory, including requests to build something with SFLO. Do not use when SFLO appears only in quoted text, documentation, examples, code, logs, or…
design
Create a doc-as-code design package from a PRD or SPEC. Conditionally generates C4 diagrams (Context/Container/Component), sequence diagrams, ER diagram + Data Dictionary, OpenAPI 3.0, AsyncAPI 3.0, ADRs, domain glossary, state diagrams, and deployment view as Mermaid-rendered Markdown files. Use when PM mentions…
tasks
A task-breakdown tool that turns a plan, specification, feature brief, bug report, technical-debt item, or chore into small TASK-NNN work items. Technical debt means postponed cleanup or design work in a codebase.
review-pr
A pull-request review skill for evaluating proposed code changes and posting a quality verdict. A pull request is a request to merge changes into a shared codebase.
understand-codebase
Understand an unfamiliar codebase or plan a change safely, using Spine's deterministic knowledge-graph MCP tools. Reach for this before answering structural questions about a repo you don't know, before editing code, or when debugging — it hands you engineering decisions (what a change breaks, what's untested, where a…