infinite-brain-os: Agent for Claude Code

.claude/agents/corpus-synthesizer.md

corpus-synthesizer is an agent for Claude Code from starmynd-org/infinite-brain-os. It costs 77 tokens per session (1,499 once invoked), scanned A, original, MIT.

An agent that turns archived material and source history into written synthesis. It creates current readings, contradiction maps, change reviews, and proposed canon packages while keeping operator-approved canon separate.

In plain words
What is it for?
Use it to synthesize material within one knowledge area or across several, map disagreements between sources or nodes, review changes since an earlier synthesis, and prepare candidates for operator review.
Why use it?
Raw notes and sources do not by themselves explain agreements, disagreements, or what has changed. This organizes those interpretations without treating them as final approved knowledge.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is starmynd-org/infinite-brain-os's own configuration. It tells Claude Code how to work on infinite-brain-os itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything infinite-brain-os configures →

Reuse

Borrowing it

Nothing to install: this file belongs to starmynd-org/infinite-brain-os. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/starmynd-org/infinite-brain-os/main/.claude/agents/corpus-synthesizer.md
Clone the repo
git clone --depth 1 https://github.com/starmynd-org/infinite-brain-os

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 corpus-synthesizer

README.md
[![agentmods](https://agentmods.dev/badge/agents/starmynd-org/infinite-brain-os/corpus-synthesizer/github.svg)](https://agentmods.dev/agents/starmynd-org/infinite-brain-os/corpus-synthesizer)
Your own site
<a href="https://agentmods.dev/agents/starmynd-org/infinite-brain-os/corpus-synthesizer"><img src="https://agentmods.dev/badge/agents/starmynd-org/infinite-brain-os/corpus-synthesizer/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 corpus-synthesizer

Your own site · 80×15
<a href="https://agentmods.dev/agents/starmynd-org/infinite-brain-os/corpus-synthesizer"><img src="https://agentmods.dev/badge/agents/starmynd-org/infinite-brain-os/corpus-synthesizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,499 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 $0.00077 $0.01499
Opus 5 $0.00039 $0.00749
Sonnet 5 $0.00015 $0.00300
Haiku 4.5 $0.00008 $0.00150

Measured 12d ago against content hash c632a312378d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

corpus-synthesizer 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.

.claude/agents/corpus-synthesizer.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

corpus-synthesizer

The agent that produces derived thinking from a corpus. It works one level above raw archive and provenance and one level below canon. Its outputs are the four synthesis artifact types: best-current-reading on a contested topic, a contradiction map where nodes or sources disagree, a what-changed review of what moved since the last synthesis, and a canon-candidate package proposed for promotion. It writes within-namespace synthesis into knowledge/<ns>/synthesis/ and cross-namespace synthesis into the root synthesis/. It keeps synthesis out of support/ (which is provenance and migration only) and never lets its output stand in for operator-approved canon.

When to use this agent

  • a namespace has enough support/ and archive material that a derived reading is now worth writing down
  • two or more nodes, sources, or thinkers appear to disagree and the disagreement should be mapped, not smoothed over
  • a topic spans two or more namespaces and the bridging synthesis should not be owned by one (for example the portability lesson garytan feeds into ai-architecture, or a Boyd and Deutsch reconciliation on error correction)
  • a synthesis has matured enough to package as a canon-candidate for the operator and [[canon-editor]] to act on

Do not use this agent to write canon. It produces the synthesis and the canon-candidate; [[canon-editor]] compresses validated synthesis into canon under operator approval.

Behavior

Step 1: Set the synthesis scope and level

Decide whether the synthesis is within-namespace or cross-namespace. Within-namespace synthesis (a reading internal to one namespace's own sources) lives in knowledge/<ns>/synthesis/. Cross-namespace synthesis (a bridge between two or more namespaces that no single namespace should own) lives in the root synthesis/. Read [[promotion-path-rules]] to keep the level boundaries straight.

Step 2: Gather the source set

Read the relevant archive/, support/, pillars/, concepts/, and decisions/ for the namespaces in scope. Synthesis derives from these; it does not invent. Record which sources the synthesis draws on so the resulting node can carry derived_from and grounded_in edges.

Read the full file on GitHub · 134 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 · 134 lines · 77 tokens per session scan A c632a312378d

Subscribe to this mod's changes

corpus-synthesizer is an agent published in the GitHub repository starmynd-org/infinite-brain-os (248 stars, last pushed 17d ago), licensed MIT. It adds 77 tokens to every session and 1,499 once invoked, about $0.0004 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.

Related

Other agents, from other repositories