agentmods.dev

kw-reader

An agent that reads one research-paper PDF and records its contents in a structured, source-linked format.

In plain words
What is it for?
Use it to extract a paper's claims, details, and section or figure references into a research memory file and update the paper index.
Why use it?
It keeps detailed paper reading separate from later summarising or comparison, while marking information that the paper does not provide as unknown.

Agent

11 2mo ago A scan 31 tokens original MIT
View the source file chenpg2/kw-engine
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/chenpg2/kw-engine/kw-reader
Clone the repo
git clone --depth 1 https://github.com/chenpg2/kw-engine
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 365 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 $0.00031 $0.00365
Opus 5 $0.00015 $0.00182
Sonnet 5 $0.00006 $0.00073
Haiku 4.5 $0.00003 $0.00036

Measured 2d ago against content hash 1e89a20de4d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kw-reader 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/kw-reader.md · 27 lines

What it actually says

You produce a FAITHFUL Layer-1 reading of ONE paper. You do NOT abstract or generalize.

You are the ONLY place a paper's full text enters context. Reading runs here, on sonnet, by design — the orchestrator must never pull paper text into the opus loop. Read the local paper/<id>.pdf only; do not call read_*/search_* MCP tools or re-fetch (kw-fetcher already acquired and validated the PDF).

Inputs you are given: a paper id and the PDF path (paper/<id>.pdf).

Procedure:

  1. Read memory/SCHEMA.md §1 and process/extract-template.md.
  2. Read the PDF (paper/<id>.pdf). If it cannot be parsed, STOP and report FAIL: cannot parse paper/<id>.pdf — do NOT emit an empty record (no silent fallback).
  3. Create memory/papers/<id>.md filling every SCHEMA §1 field. Cite section/figure locators for each claim. Use UNKNOWN + status: incomplete for anything not in the text.
  4. Update index.json: set that paper's status to L1, fill title/doi if found. (Validate JSON after writing: python3 -m json.tool memory/index.json >/dev/null.)

Your final message: the path written, status, and any UNKNOWN fields. Nothing else.

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 · 27 lines · 31 tokens per session scan A 1e89a20de4d3

Subscribe to this mod's changes

kw-reader is an agent published in the GitHub repository chenpg2/kw-engine (11 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 365 once invoked, about $0.0002 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.

Data and AIDocumentsMemory and contextactive-learningclaude-codeknowledge-managementllm-agentsmethodologyresearch-tools
Related

Other agents, from other repositories

00-session-bootstrap

Recover state from previous session including action cards, missed debriefs, and loop escalation.

assafkip/kipi-system · 21 tokens

grounded-review-writer

Apply reviewer-approved repairs to the research report draft for grounded-review while preserving substance.

gaotiexinqu/OneResearchClaw · 22 tokens

agent-registry-auditor

Audits agents for DIP-0016 compliance and registry alignment. Use this agent when: Adding a new agent to the system Checking if existing agents need registry entries Validating spawn relationships and circular dependencies Generating missing registry entries Upgrading agents with Agent Context sections This agent…

datacore-one/datacore · 84 tokens

youtube-transcriber

Sub-agent that extracts transcripts and metadata from YouTube videos and playlists. Uses youtube-transcript-api for captions and yt-dlp for metadata. Returns structured markdown with metadata.

datacore-one/datacore · 38 tokens

gan-harness

You are a GAN-style adversarial multi-agent harness coordinator. You orchestrate three phases — Plan, Generate, Evaluate — in iterative cycles to produce high-quality output.

datacore-one/datacore · 0 tokens

domain

Single-context layout: one CONTEXT.md and one docs/adr/ at the repo root.

pumblus/okf-harness · 0 tokens