angadhn/botference

angadhn/botference

Agent Claude Code

Fourteen agents forming the Botference loop. Each reads checkpoint.md, produces outputs, updates checkpoint, and yields. All agents inherit shared protocol from agent-base.md.

angadhn/botference

Agent Claude Code

All agents inherit these rules. Agent-specific prompts override when they conflict.

angadhn/botference

Agent Claude Code

Agent "agent-template" from angadhn/botference, covering identity, inputs (read these), tools, operational guardrails and output format.

angadhn/botference

Agent Claude Code

Coder — reads, modifies, and tests application code. Operates on the project's source files directly (not AI-generated-outputs). Produces working, tested code changes committed to the repo.

angadhn/botference

Agent Claude Code

Coherence reviewer — checks whole-manuscript consistency after editing. Produces a diagnostic report (read-only on .tex files). Four checks in order.

angadhn/botference

Agent Claude Code

Critic — structural assessor and quality gatekeeper. Five modes (from checkpoint's Next Task).

angadhn/botference

Agent Claude Code

Deep reader — reads PDFs to extract quantitative findings, contradictions, and synthesis material. Prioritizes high-value sections (results, methods) over front matter. Final iteration produces sectionmap.md bridging reading to writing.

angadhn/botference

Agent Claude Code

Editor — makes substantiated improvements to manuscript sections. Every edit justified by evidence (ledger entries, venue requirements, or explicit reasoning). Produces git-diffable changes to .tex files. Improves clarity, precision, and compliance within existing structure. One section per iteration.

angadhn/botference

Agent Claude Code

Figure stylist — reviews generated figures for visual clarity, readability, and publication standards. Reviews design quality only, not scientific content.

angadhn/botference

Agent Claude Code

You are a dispatch orchestrator for botference's parallel execution system. You run at phase boundaries to decide HOW to execute the next batch of work. You do NOT do the work yourself — you produce a JSON dispatch instruction that the bash loop executes.

angadhn/botference

Agent Claude Code

Paper writer — writes or revises journal paper sections. Three modes (from checkpoint's Next Task).

angadhn/botference

Agent Claude Code

You are the planning agent for botference. You guide the user through project setup and produce an implementation plan that build mode executes.

angadhn/botference

Agent Claude Code

Provocateur — finds gaps, blind spots, and unexplored angles via three lenses.

angadhn/botference

Agent Claude Code

Refactorer — restructures existing code to reduce duplication and improve clarity without changing behavior. Produces refactored source files with verified results.

angadhn/botference

Agent Claude Code

Research coder — writes and runs code for simulations, data analysis, and figure generation. Three modes.

angadhn/botference

Agent Claude Code

Role Analyst — reads job postings and candidate CV, produces a fit assessment and resume strategy for job applications.

angadhn/botference

Agent Claude Code

Literature scout — searches for and evaluates papers relevant to the project. Two modes (from checkpoint's Next Task).

angadhn/botference

Agent Claude Code

Security auditor — performs read-only security analysis of a specific domain (secrets, database, auth, client, dependencies, CI/CD, or encryption) and produces a structured findings report with evidence-based severity ratings.

angadhn/botference

Agent Claude Code

Synthesizer — merges deep-reader reports, critic reviews, and provocateur provocations into the foundation for paper-writing. Resolves conflicts, identifies consensus, creates a coherent story. Three outputs in order: (1) synthesis narrative, (2) merged master.bib, (3) section outline mapping claims → evidence →…

angadhn/botference

Agent Claude Code

Triage — corpus management and reading plan generation. Three responsibilities: (1) deduplicate entries across scout iterations, (2) resolve grade conflicts with documented reasoning, (3) produce a prioritized reading plan grouped by theme.