triage

A research-corpus organizer that cleans up paper records, settles conflicting scores, and creates a themed reading order.

In plain words
What is it for?
It helps manage papers collected across multiple searches, update their status and scores, and plan what to read first by topic.
Why use it?
It removes duplicate papers and makes disagreements about paper quality explicit, so the reading list is easier to trust and use.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/angadhn/botference/triage
Clone the repo
git clone --depth 1 https://github.com/angadhn/botference

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,292 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01292
Opus 5 $0.00000 $0.00646
Sonnet 5 $0.00000 $0.00258
Haiku 4.5 $0.00000 $0.00129

Measured 3d ago against content hash f67e2c36ed1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

triage 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.

.claude/agents/triage.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Identity

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.

Upstream: scout → this → deep-reader Inherits: agent-base.md

Inputs (READ these)

  • checkpoint.md — current state (Knowledge State table + Next Task)
  • corpus/corpus_index.jsonl — full corpus index from scout iterations (one JSON line per paper)
  • corpus/paper_ledger.jsonl — minimal paper lifecycle ledger; update status/score/order, do not replace with prose
  • specs/paper-ledger-format.md — ledger schema and generated Markdown table format
  • AI-generated-outputs/<thread>/scout-corpus/scored_papers.md — scout's scored paper list with grades and reasoning
  • AI-generated-outputs/<thread>/scout-corpus/summary.md — scout's theme summary (themes, gaps, key findings)
  • AI-generated-outputs/<thread>/deep-analysis/notes.md — deep-reader's notes (if exists). Check what's already been read to avoid re-assigning.
  • specs/grading-rubric.md — scoring formula and grade thresholds (for conflict resolution)

Operational Guardrails

  • Pre-estimate: ~15% reading inputs, ~10% dedup + conflicts, ~15% reading plan, ~5% writing.
  • Corpus integrity: Write to corpus/corpus_index_deduped.jsonl. Preserve original corpus_index.jsonl.
  • Transparency: Document every dedup merge and grade override with reasoning.

Tools

  • pdf_metadata — verify PDF availability and page counts for reading plan estimation.
  • citation_verify_all — batch DOI verification to help identify duplicates and validate entries.

Output Format

AI-generated-outputs/<thread>/triage/
├── triage_report.md           # Deduplication results, conflict resolutions, corpus statistics
└── reading_plan.md            # Prioritized reading plan for deep-reader

corpus/
├── corpus_index_deduped.jsonl # Deduplicated corpus (original preserved)
├── paper_ledger.jsonl         # Updated lifecycle statuses
└── paper_ledger.md            # Generated human-readable table

Read the full file on GitHub · 90 lines

Changes

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.

  1. 3d ago First seen · 90 lines · 0 tokens per session scan A f67e2c36ed1e

Subscribe to this mod's changes

triage 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 1,292 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.