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.
git clone --depth 1 https://github.com/chenpg2/kw-engineWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/chenpg2/kw-engine/kw-reader)<a href="https://agentmods.dev/agents/chenpg2/kw-engine/kw-reader"><img src="https://agentmods.dev/badge/agents/chenpg2/kw-engine/kw-reader/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/chenpg2/kw-engine/kw-reader"><img src="https://agentmods.dev/badge/agents/chenpg2/kw-engine/kw-reader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00031 | $0.00365 |
| Opus 5.5 | $0.00012 | $0.00146 |
| Sonnet 5.5 | $0.00006 | $0.00073 |
| Haiku 4.5 | $0.00003 | $0.00036 |
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 1mo 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.
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:
- Read
memory/SCHEMA.md§1 andprocess/extract-template.md. - Read the PDF (
paper/<id>.pdf). If it cannot be parsed, STOP and reportFAIL: cannot parse paper/<id>.pdf— do NOT emit an empty record (no silent fallback). - Create
memory/papers/<id>.mdfilling every SCHEMA §1 field. Cite section/figure locators for each claim. UseUNKNOWN+status: incompletefor anything not in the text. - Update
index.json: set that paper'sstatustoL1, filltitle/doiif 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.
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.
- 1mo ago First seen · 27 lines · 31 tokens per session scan A 1e89a20de4d3
kw-reader is an agent published in the GitHub repository chenpg2/kw-engine (11 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 365 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other agents, from other repositories
knowledge-extractor
Coordinator agent that routes content to specialized sub-agents and produces structured knowledge artifacts (literature notes, atomic zettels, action items). Takes any content type — URL, PDF, conversation export, local file, or raw text.
search
Search agent that retrieves candidates, verifies metadata, acquires permitted PDFs, converts readable text, and produces the refpapers material package with a durable per-paper factual handoff.
pdf-extractor
Sub-agent that extracts structured text from PDF files. Preserves document structure, handles tables, and detects OCR needs. Returns structured markdown with metadata.
ocr-reader
Sub-agent that extracts text from image files and scanned PDFs using the Datacore OCR MCP server (Tesseract). Called by file-reader for images and pdf-extractor for scanned PDFs.
visualization-agent
Parses paper data and statistical results to generate publication-quality figure code in Python (matplotlib/seaborn) or R (ggplot2) formatted to APA 7.0 standards, producing accessible, colorblind-safe visualizations with captions, labels, and LaTeX inclusion code.
quarto-critic
Adversarial QA agent that compares Quarto HTML against Beamer PDF benchmark. Produces harsh, actionable criticism. Does NOT edit files — read-only analysis only.