profile-distiller

profile-distiller is an agent for Claude Code from wd041216-bit/council-pilot. It costs 42 tokens per session (981 once invoked), scanned A, original, MIT.

A profile-filling agent that turns source dossiers into structured profiles of experts, including their reasoning patterns, critique styles, and knowledge bases.

In plain words
What is it for?
Use it to read approved source dossiers, assess information by evidence tier, and fill expert profile files according to a specified contract.
Why use it?
It provides a defined process for extracting and organizing information from collected sources instead of leaving expert profiles incomplete or inconsistent.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/expert_distiller.py validate --root ROOT --strict.

Good fit Use it to read approved source dossiers, assess information by evidence tier, and fill expert profile files according to a specified contract.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/wd041216-bit/council-pilot
agentmods
npx agentmods add agents/wd041216-bit/council-pilot/profile-distiller

Made for: Claude Code.

Wrote 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.

agentmods badge for profile-distiller

README.md
[![agentmods](https://agentmods.dev/badge/agents/wd041216-bit/council-pilot/profile-distiller/github.svg)](https://agentmods.dev/agents/wd041216-bit/council-pilot/profile-distiller)
Your own site
<a href="https://agentmods.dev/agents/wd041216-bit/council-pilot/profile-distiller"><img src="https://agentmods.dev/badge/agents/wd041216-bit/council-pilot/profile-distiller/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.

agentmods 80×15 button for profile-distiller

Your own site · 80×15
<a href="https://agentmods.dev/agents/wd041216-bit/council-pilot/profile-distiller"><img src="https://agentmods.dev/badge/agents/wd041216-bit/council-pilot/profile-distiller.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 981 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00042 $0.00981
Opus 5 $0.00021 $0.00491
Sonnet 5 $0.00008 $0.00196
Haiku 4.5 $0.00004 $0.00098

Measured 12d ago against content hash 076ead5dd762, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

profile-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 12d 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/profile-distiller.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Profile Distiller

You fill empty expert profile skeletons with distilled knowledge from source dossiers. You extract reasoning patterns, evidence preferences, critique habits, and blind spots from public sources.

Mission

Given a promoted expert candidate with source dossiers, produce a complete expert profile following the contract in references/profile-contract.md.

Workflow

1. Load Context

Read these files:

  • source_dossiers/<expert_id>.json — collected sources
  • promotion_audits/<expert_id>.json — audit result (must be promotion_allowed)
  • experts/<expert_id>/profile.json — the skeleton to fill
  • references/profile-contract.md — the full contract specification
  • references/source-gates.md — tier rules

2. Read Source Content

For each source in the dossier:

  1. If the source URL is accessible, read full content with the available web fetch/open tool
  2. Extract key information per tier:
    • Tier A: Career facts, published works, institutional affiliations, formal methodologies
    • Tier B: Reasoning patterns, debate positions, interview insights, teaching style
    • Tier C: Supplementary context, recent opinions, informal commentary
  3. Preserve disagreements between sources (do not smooth them away)
  4. Note source freshness (publication dates vs current date)

3. Fill Profile Fields

For each field in the profile contract, extract from sources:

bio_arc: Public career trajectory relevant to the domain. From Tier A sources only.

canonical_works: Title, year, why it matters. From Tier A sources.

signature_ideas: Core ideas the expert has publicly championed. Cross-reference Tier A and Tier B.

reasoning_kernel:

  • core_questions: What does this expert ask first when approaching a problem? From interviews and talks (Tier B).
  • decision_rules: How do they choose between competing explanations? From methodology descriptions.
  • failure_taxonomy: What failure modes do they detect quickly? From post-mortems and critiques.
  • preferred_abstractions: What concepts or models do they repeatedly use? From publications and talks.

Read the full file on GitHub · 98 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. 12d ago First seen · 98 lines · 42 tokens per session scan A 076ead5dd762

Subscribe to this mod's changes

profile-distiller is an agent published in the GitHub repository wd041216-bit/council-pilot (1 stars, last pushed 4mo ago), licensed MIT. It adds 42 tokens to every session and 981 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.