knowledge-distiller

An independent assistant for turning evidence from product hypotheses into clearly scoped learnings and identified contradictions.

In plain words
What is it for?
Use it during reflection to compare concluded hypotheses, track confidence changes and contexts, summarise supported outcomes, document conflicting evidence, and assess whether a learning should be promoted.
Why use it?
It separates evidence synthesis from the person who created the hypothesis, reducing the chance that conclusions simply repeat the original expectations.

Agent for Cursor

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/shinpr/nautilus/knowledge-distiller
Clone the repo
git clone --depth 1 https://github.com/shinpr/nautilus

Made for: Cursor.

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 393 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 $0.00393
Opus 5 $0.00015 $0.00197
Sonnet 5 $0.00006 $0.00079
Haiku 4.5 $0.00003 $0.00039

Measured 3d ago against content hash 2fca403acfb8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

knowledge-distiller 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.

.cursor/agents/knowledge-distiller.md · 44 lines

What it actually says

You compare hypothesis evidence in a separate context and return only supported learnings and contradictions.

Required Skills [LOAD BEFORE EXECUTION]

  1. [LOAD IF NOT ACTIVE] product-principles — Knowledge Pyramid, Tier definitions, distillation criteria

Responsibilities

  1. Distill supported learnings and contradictions with source hypotheses.
  2. Propose a Tier promotion only when the governing criteria are met.

Distillation Process

Step 1: Gather Evidence

Start from the Opportunity, then read the hypothesis files needed to assess candidate learnings and contradictions:

  • Focus on concluded hypotheses (validated/invalidated/inconclusive/adopted/rejected)
  • Note the evidence and confidence changes
  • Track which segments/contexts each hypothesis covers

Step 2: Learning Synthesis

Synthesize corroborated outcomes into candidate learnings and conflicting evidence into contradictions. For each candidate learning:

  1. State the learning clearly and concisely
  2. List supporting hypotheses (with IDs)
  3. State the contexts, conditions, or limitations that bound it
  4. Assess Tier promotion eligibility

Step 3: Promotion Assessment

Promote to Tier 1 when independent evidence supports the learning across its intended decision scope and material contradictions are conditioned. Keep narrower evidence at Tier 2.

Output

Return one compact JSON object. Keep source hypotheses explicit.

{"learnings":[{"statement":"distilled learning","tier":"tier1|tier2","sources":["HYPO-NNN"],"contexts":["scope condition or limitation"]}],"contradictions":[{"description":"conflicting evidence","sources":["HYPO-NNN"],"conditions":["condition that explains the difference"],"decision_effect":"decision this can change"}]}
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 · 44 lines · 31 tokens per session scan A 2fca403acfb8

Subscribe to this mod's changes

knowledge-distiller is an agent published in the GitHub repository shinpr/nautilus (4 stars, last pushed 4d ago), licensed MIT. It adds 31 tokens to every session and 393 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 2026-08-31.

Related

Other agents, from other repositories

research-expander

Task-specific research subagent for the prd-taskmaster expand-tasks skill. Takes a TaskMaster task (title, description, dependencies) and runs 3-5 targeted queries via available research tools (task-master research, MCP search/reason, WebSearch). Returns structured summary (25-40 lines) with citations suitable for…

anombyte93/prd-taskmaster · 80 tokens

prototype-generator

Generates self-contained HTML prototypes for hypothesis validation. Reads project design context files and produces a product UI that users interact with naturally. Context separation ensures prototypes reflect product vision. Invoked by recipe-validate for Usability risk validation.

shinpr/claude-code-discover · 49 tokens

ylc

Deep learning pioneer. VP and Chief AI Scientist at Meta (since 2013). Silver Professor at NYU. Co-developer with Geoffrey Hinton and Yoshua Bengio of the modern deep-learning paradigm — recognized with the 2018 ACM Turing Award. Inventor of convolutional neural networks (LeNet, late 1980s), the practical use of…

punt-labs/prfaq · 107 tokens

hypothesis-verifier

Independently decomposes hypotheses into testable assumptions and designs the smallest disconfirming tests. Mandatory during recipe-validate so the authoring context does not replace a separate evidence pass.

shinpr/claude-code-discover · 42 tokens

knowledge-distiller

Independently analyzes hypothesis groups for cross-cutting patterns, contradictions, and Tier promotion evidence. Mandatory for Level 2/3 reflection so orchestration prose does not replace source artifacts.

shinpr/claude-code-discover · 41 tokens

prd-reviewer

Reviews every recipe-define PRD for governing-outcome integrity, evidence, downstream usability, and verifiability. Invoked as the mandatory independent review before user approval.

shinpr/claude-code-discover · 38 tokens