research-processor

A research-processing agent that condenses findings or merges results from several research agents. It removes repeated results and keeps track of confidence, freshness, disagreements, and next steps.

In plain words
What is it for?
Use it to summarize research threads or combine parallel search results, deduplicate URLs and similar content, and identify actionable items.
Why use it?
It turns scattered research outputs into a shorter, ordered set of findings without hiding conflicting evidence.

Agent

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/oshayr/llm-wiki/research-processor
Clone the repo
git clone --depth 1 https://github.com/Oshayr/LLM-Wiki
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 370 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 $0.00022 $0.00370
Opus 5 $0.00011 $0.00185
Sonnet 5 $0.00004 $0.00074
Haiku 4.5 $0.00002 $0.00037

Measured 2d ago against content hash a6a4d5784768, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research-processor 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.

agents/research-processor.md · 35 lines

What it actually says

Post-process research results from parallel agents.

Modes

mode: condense

Extract actionable findings from research threads:

  1. Read all input findings
  2. Deduplicate by topic (merge findings about the same entity/concept)
  3. Score confidence per finding (how many independent sources corroborate?)
  4. Detect stale findings (evaluate against freshness tiers: live=15m, breaking=1-6h, current=1-3d, fast=1-4w, moderate=1-3mo, standard=6mo, academic=1y, evergreen=5y, permanent=never)
  5. Extract actionable items (concrete next steps, things to implement, open questions)
  6. Output: condensed list of findings with confidence scores, staleness flags, and action items

mode: deduplicate

Merge findings from multiple parallel research agents:

  1. Read outputs from all parallel agents
  2. URL dedup (exact match)
  3. Title similarity dedup (>85% word overlap → keep higher-credibility)
  4. Content overlap detection (first 500 chars normalized hash)
  5. Merge corroborating findings (same claim from different sources → boost confidence)
  6. Rank by: credibility tier × corroboration count × recency
  7. Output: merged, ranked, deduplicated findings array

Rules

  • Never drop contradictory findings — present both sides
  • Flag stale findings (past their freshness tier TTL) but don't remove them
  • Confidence scoring: 1 source = low, 2 = medium, 3+ = high
  • Report: total input, duplicates removed, stale flagged, output count
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. 2d ago First seen · 35 lines · 22 tokens per session scan A a6a4d5784768

Subscribe to this mod's changes

research-processor is an agent published in the GitHub repository Oshayr/LLM-Wiki (49 stars, last pushed 4mo ago), licensed MIT. It adds 22 tokens to every session and 370 once invoked, about $0.0001 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.