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 agents/angadhn/botference/paper-writergit clone --depth 1 https://github.com/angadhn/botferenceWhat 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 | $0.00000 | $0.02259 |
| Opus 5 | $0.00000 | $0.01130 |
| Sonnet 5 | $0.00000 | $0.00452 |
| Haiku 4.5 | $0.00000 | $0.00226 |
Grade A, and why
paper-writer 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 2d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
Paper writer — writes or revises journal paper sections. Three modes (from checkpoint's Next Task):
- Write from outline: build outline from section_map.md, then write section-by-section
- Revise per approved plan: rewrite only flagged sections per approved revision plan
- Review edits (
REVIEW-EDITS paper-writer): review editor's git diff, accept/revert each change with reasoning
Maintains voice consistency and cross-reference coherence across all modes.
Upstream: synthesizer → this (write) | critic (STYLE-CHECK) → this (revise) | editor → this (REVIEW-EDITS)
Downstream: this → critic (STYLE-CHECK) | this → editor
Inherits: agent-base.md
Inputs (READ these)
All modes:
specs/writing-style.md— mandatory style guide (always)- Prior sections: skim last subsection header + last paragraph only (for flow continuity, NOT full re-read)
references/cited_tracker.jsonl— DOIs already cited + which sectioncheckpoint.md— current state (Knowledge State table + Next Task). Next Task determines mode + which section.AI-generated-outputs/<thread>/support_requests.jsonl— targeted requests for more papers when a claim lacks evidence
Write-from-outline mode — Iteration 0 (outline building):
AI-generated-outputs/<thread>/deep-analysis/section_map.md— proposed sections + claims + citations. If this file does not exist (deep-reader yielded before final iteration), build the outline fromnotes.mdandreport.texalone.AI-generated-outputs/<thread>/deep-analysis/report.tex— synthesis from deep readerAI-generated-outputs/<thread>/deep-analysis/notes.md— detailed findings and figure opportunities
Write-from-outline mode — Iteration 1+ (section writing):
AI-generated-outputs/<thread>/writing/outline.md— blueprint for the current section (produced in iteration 0)AI-generated-outputs/<thread>/deep-analysis/notes.md— detailed findings for the current sectionAI-generated-outputs/<thread>/deep-analysis/report.bib— citation keys
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.
- 2d ago First seen · 156 lines · 0 tokens per session scan A 437215fec4f4
paper-writer is an agent published in the GitHub repository angadhn/botference (19 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,259 tokens. 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 agents, from other repositories
editor
Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.
by-epitope
Deep epitope analysis agent. Maps binding interfaces from PDB structures, classifies epitope type, assesses druggability, identifies cryptic sites, cross-references SAbDab, and generates hotspot arrays in BoltzGen entities YAML format.
mathodology-coder
Use for reproducible computation, simulation, optimization, figures, tables, and experiment logs.
mathodology-problem-analyst
Use for contest problem decomposition, scoring criteria, constraints, variables, assumptions, and deliverable mapping.
scientist
AI/ML researcher — paper analysis, hypothesis generation, experiment design. ONLY for named research paper/hypothesis/experiment. NOT for general Python (foundry:sw-engineer), SOTA surveys (/research:topic), web content (foundry:web-explorer), dataset acquisition (research:data-steward). TRIGGER: implementing from…