Borrowing it
Nothing to install: this file belongs to RipeMangoBox/BITE. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/RipeMangoBox/BITE/main/.claude/skills/papers-collect-from-web/SKILL.mdgit clone --depth 1 https://github.com/RipeMangoBox/BITEWrote 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/ripemangobox/bite/papers-collect-from-web)<a href="https://agentmods.dev/skills/ripemangobox/bite/papers-collect-from-web"><img src="https://agentmods.dev/badge/skills/ripemangobox/bite/papers-collect-from-web/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/ripemangobox/bite/papers-collect-from-web"><img src="https://agentmods.dev/badge/skills/ripemangobox/bite/papers-collect-from-web.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 | $0.00108 | $0.00961 |
| Opus 5.5 | $0.00043 | $0.00384 |
| Sonnet 5.5 | $0.00022 | $0.00192 |
| Haiku 4.5 | $0.00011 | $0.00096 |
Grade A, and why
papers-collect-from-web 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Collector (Online / Web)
Fetch web pages to local storage, extract paper candidates, and append them to obsidian-vault/paper_list.csv.
Use this skill for non-GitHub web sources: conference sites, lab homepages, proceedings pages (ACL Anthology, IEEE Xplore, etc.), Google Scholar results, blog posts with paper lists, etc.
For GitHub repositories (awesome lists, survey repos, lab paper repos, conference paper repos), use papers-collect-from-github-repo instead — it handles raw Markdown and multi-file repo structures better.
Scope
- Input: one or more web URLs + include/exclude keyword constraints + target venue/year label.
- Output:
- saved source pages under
paperSources/<run_id>/... - new rows appended to
obsidian-vault/paper_list.csv
- saved source pages under
Output format (CSV columns, same as paper_list.csv)
state,importance,paper_title,venue,project_link_or_github_link,paper_link,sort,pdf_path
Defaults:
- state:
Wait(newly collected) orSkip(manually marked skip) - importance: empty (user fills later)
- venue: user-provided label such as
ICLR 2026 - sort: leave blank if unknown; user can fill per item later
- pdf_path: empty (filled later by
papers-download-from-list)
State convention is defined in
STATE_CONVENTION.md: main pipelineWait → Downloaded → analysised → checked; out-of-band statesSkip/Missing.
Workflow
- Ask user for:
- URLs (one or many)
- include keywords (optional) and exclude keywords (optional)
- venue/time label (for example
ICLR 2026) - whether to overwrite or append if rows already exist for this venue
- Run collector script (preferred default):
python3 ".claude/skills/papers-collect-from-web/scripts/paper_collector_online/collect_from_urls.py" --venue-time "ICLR 2026" --urls "<URL1>" "<URL2>" --include "motion;diffusion" --exclude "workshop;dataset" --append
- Verify generated rows:
- columns present and in correct order
- dedup applied by normalized paper link against existing
paper_list.csv - links are well-formed (no surrounding punctuation)
- If extraction quality is poor for a URL:
- rerun with tighter keywords, or
- run per-source URLs separately, or
- manually provide a short snippet list and extend script patterns only if needed.
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.
- 1mo ago First seen · 73 lines · 108 tokens per session scan A aaba8d6d8a55
papers-collect-from-web is a skill published in the GitHub repository RipeMangoBox/BITE (62 stars, last pushed 2mo ago), licensed MIT. It adds 108 tokens to every session and 961 once invoked, about $0.0004 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
llm-wiki
Explain and apply the foundational LLM Wiki architecture and knowledge-management strategy. Use for setup, architecture, schema, or organization decisions; operational ingest/query/lint work uses dedicated skills.
wiki-lint
Audit wiki health: broken links, orphans, contradictions, stale content, lifecycle and tag issues. Use for maintenance or health checks. Default is report-only; use wiki-dedup for page-identity merges.
wiki-export
Export the Obsidian wiki graph to JSON, GraphML, Neo4j Cypher, Postgres/SQL, HTML, or OKF bundles. Use when transferring or visualizing wiki data in external tools; wiki-import handles the reverse direction.
wiki-status
Report wiki ingestion/completeness state, pending source delta, structural insights, or maintenance equilibrium. Use for remaining-work/status questions, hubs and bridges, or whether maintenance skills still have pending changes. wiki-digest summarizes learned knowledge instead.
wiki-query
Search and synthesize answers from the compiled Obsidian wiki, including cited and multi-hop answers. Use for questions about existing wiki knowledge or fast index-only lookups, and for challenge requests ("challenge this", "argue against X", "poke holes in my plan") that look for the vault's own evidence against a…
wiki-import
Import a wiki graph into the current vault from graph.json or an OKF/markdown bundle. Use for transferring previously exported wiki content between vaults; pair with wiki-export for the reverse direction.