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 paper-research-formgit 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/paper-research-form)<a href="https://agentmods.dev/skills/nanoagentteam/research-claw/paper-research-form"><img src="https://agentmods.dev/badge/skills/nanoagentteam/research-claw/paper-research-form/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/paper-research-form"><img src="https://agentmods.dev/badge/skills/nanoagentteam/research-claw/paper-research-form.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 | $0.00182 | $0.00813 |
| Opus 5 | $0.00091 | $0.00407 |
| Sonnet 5 | $0.00036 | $0.00163 |
| Haiku 4.5 | $0.00018 | $0.00081 |
Grade A, and why
paper-research-form 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.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
[SKILL: PAPER RESEARCH FORM — CSV LITERATURE SURVEY]
Generate a literature survey as a CSV file and deliver the file to the user in chat.
Keep this file lean. Load the reference documents only when reaching the matching step.
Workflow
1. Clarify Scope
Confirm these inputs if the user has not already specified them:
- research topic or keywords
- target venues or
any - year range
- paper count
Use these defaults when needed:
- year range: last 3 years
- paper count: 10-15
2. Search And Verify
Load references/search-strategy.md before broad search.
Search multiple sources, then verify metadata for each candidate paper.
Use web_fetch on promising results to verify:
- title
- authors
- abstract
- venue
- year
- canonical link
Never fabricate metadata. Skip weak candidates that cannot be verified.
3. Build Rows
Load references/csv-schema.md before writing any row.
Transform each verified paper into one CSV row using the required 8-column schema. Write the summary in original wording. Rate relevance against the user's actual research goal.
4. Merge Or Create Output
Load references/merge-and-delivery.md before selecting the output file.
Append by default:
- look for matching
survey_*.csvfiles - pick the newest matching file
- skip duplicate titles
- create a new file only when no match exists or the user requests a new survey direction
5. Write CSV
Write the final CSV with:
- UTF-8 BOM
- correct CSV escaping
- rows sorted by relevance first, then year descending
6. Deliver File
This step is mandatory.
- Call
send_fileimmediately afterwrite_file - Retry once if
send_filefails - Do not claim the file was sent unless
send_fileactually returned success - Do not continue to the report step until
send_filehas actually been called
7. Report
After file delivery, report:
- total papers found
- relevance breakdown
- top 3 most relevant papers
- gaps or follow-up searches
Reference Files
Load only the file needed for the current step:
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 112 lines · 182 tokens per session scan A 96d7024f55aa
paper-research-form is a skill published in the GitHub repository nanoAgentTeam/research-claw (292 stars, last pushed 3mo ago), licensed MIT. It adds 182 tokens to every session and 813 once invoked, about $0.0009 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
dcf-model
Build discounted cash flow valuation workbooks in Excel.
comps-analysis
Build comparable-company valuation workbooks in Excel.
lbo-model
Build leveraged buyout workbooks with IRR/MOIC in Excel.
google-workspace
Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.
excel-author
Build auditable financial workbooks headless via openpyxl.
xlsx
Create, read, edit Excel .xlsx workbooks and CSVs.