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 agentmods add skills/ripemangobox/bite/research-workflownpx skills add RipeMangoBox/BITE --skill research-workflowgit clone --depth 1 https://github.com/RipeMangoBox/BITEWhat 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 | $0.00069 | $0.01206 |
| Opus 5 | $0.00034 | $0.00603 |
| Sonnet 5 | $0.00014 | $0.00241 |
| Haiku 4.5 | $0.00007 | $0.00121 |
Grade A, and why
research-workflow 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 3d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Workflow Entry
Use this as the single entry for local research workflow orchestration.
Route to file-based skills and their obsidian-vault/ outputs.
It does not replace underlying skills. It routes to them with a clear stage model.
Stage model
KB build chain:
- collect / import local PDFs → download when needed → analyze → (optional build)
- note: there is no dedicated library-sync skill. If the user already has PDFs, ask for the PDF folder path and register/copy them into the local vault layout.
KB usage chain:
- query (including comparison requests) → ideate → focus → review
Support chain:
- audit / export / code-context
Purpose
- Provide one understandable entry point for the full workflow.
- Support both:
- step-by-step execution (specify a stage)
- end-to-end guidance (auto-detect next stage)
- Clarify each stage's input/output contract.
- Avoid overlap: orchestration here, execution in existing stage skills.
Stage mapping (reuse existing skills)
- import local PDFs
- Ask the user for the PDF folder path, category/sort hint, and venue/year
hint. Use the local vault layout and
paper_list.csvconvention. - External libraries such as resmax are imported through an adapter/migration step. Keep their roots explicit; do not add repository-specific defaults to the core analysis runner.
- Ask the user for the PDF folder path, category/sort hint, and venue/year
hint. Use the local vault layout and
- collect
papers-collect-from-webpapers-collect-from-github-repo
- download
papers-download-from-list
- analyze
- default route:
scripts/run_local_paper_analysis.pyformal analysis chain (MinerU parse/reuse → chunk anchor extraction → main analysis JSON → section writers → DeepSeek figure/table placement review → vault export and validation) - batch queue route:
scripts/run_paper_list_analysis.py --state Downloadedwrites per-row results underobsidian-vault/batches/<run_id>/and leavespaper_list.csvunchanged until reviewed consolidation. - note: after analyze, you can go directly to query; run build only if you need refreshed indexes
- default route:
- build
papers-build-index(refreshes bothobsidian-vault/index/index.jsonlfor agents and Obsidian navigation pages)
- query
papers-query-knowledge-base(also handles comparison and code-context requests)
- ideate
research-brainstorm-from-kb
- focus
idea-focus-coach(can be used independently; does not depend on ideate output)
- review
reviewer-stress-test(can be used independently; does not depend on focus output)
- audit
papers-audit-metadata-consistency
- export
notes-export-share-version
What ships with it
1 file 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.
- 3d ago First seen · 139 lines · 69 tokens per session scan A a332fb274a49
research-workflow is a skill published in the GitHub repository RipeMangoBox/BITE (60 stars, last pushed 20d ago), licensed MIT. It adds 69 tokens to every session and 1,206 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
compile-wiki
Merge source summaries into durable concept pages with backlinks, index entries, and explicit open questions.
ingest-sources
Review newly ingested raw sources and draft or update source summary notes in notes/Sources/.
qa-agent
Answer questions from the vault, then file durable insights back into the knowledge base.
research-workflow
Manage resumable research runs under research/ and coordinate the collect, review, report, import, and archive steps.
lint-heal
Scan the vault for contradictions, unsupported claims, structural weaknesses, and missing pages, then repair what is safe.
render-output
Convert vault content into downstream outputs like memos, reports, slide outlines, diagrams, and plot specifications.