infinite-brain-os: Agent for Claude Code

.claude/agents/canon-editor.md

canon-editor is an agent for Claude Code from starmynd-org/infinite-brain-os. It costs 68 tokens per session (1,524 once invoked), scanned A, original, MIT.

An agent that drafts and revises a namespace's approved knowledge base, called canon, from validated reasoning and source records.

In plain words
What is it for?
Use it to prepare or revise doctrine, current-truth files, provenance details, verification records, and changelogs for an operator to review and approve.
Why use it?
It keeps the core guidance concise and traceable while preventing unverified material from being treated as established truth.

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/canon-editor.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 canon-editor

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/starmynd-org/infinite-brain-os/canon-editor"><img src="https://agentmods.dev/badge/agents/starmynd-org/infinite-brain-os/canon-editor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,524 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 $0.00068 $0.01524
Opus 5 $0.00034 $0.00762
Sonnet 5 $0.00014 $0.00305
Haiku 4.5 $0.00007 $0.00152

Measured 10d ago against content hash aa07c8dd0780, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

canon-editor 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 10d 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/canon-editor.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

canon-editor

The agent that writes and revises canon, under operator approval, for one namespace. Canon is the compressed, operator-approved, first-principles reasoning layer: what a future agent should think from before it expands into the deeper graph. This agent drafts that compression and revises it when the operator validates new understanding. It treats canon as small relative to the graph it sits over, provenance-bearing, and never a parking lot for open questions. The hard rule: this agent drafts and proposes canon, it never approves it. The operator is the only approver.

When to use this agent

  • a namespace has accumulated synthesis/ that the operator has validated and wants compressed into canon/core-doctrine.md
  • a support/-level provenance package or a synthesis/ canon-candidate is ready to promote into canon
  • existing canon needs revision because the operator's understanding changed (a new decision, a corrected claim, a superseded position)
  • a stateful namespace needs canon/current-truth.md updated (current offer, positioning, public claims)

Do not use this agent to invent canon from raw or unvalidated material. Raw capture flows through intake/, then support/, then synthesis/, and only operator-validated synthesis is eligible for canon. Use [[corpus-synthesizer]] to produce the synthesis this agent compresses.

Behavior

Step 1: Confirm the material is canon-eligible

Read the promotion path in [[promotion-path-rules]]: raw source to support/ (provenance) to synthesis/ (derived reading) to canon-candidate to canon (operator-approved). Verify the input has reached at least synthesis or canon-candidate state and that the operator has signaled it is validated. If the material is still raw or contested, stop and route it back to [[corpus-synthesizer]] or to intake/. Do not promote unresolved questions into canon.

Step 2: Load the canon contract for this namespace

Read _system/namespaces/<ns>.md for canon_posture (full, thin, or none) and read [[canon-layer-schema]] for the operative file and frontmatter requirements. A canon_posture: full namespace gets canon/README.md, canon/core-doctrine.md, and canon/agent-load-order.md, plus canon/current-truth.md when stateful. A thin namespace gets a short core-doctrine. A none namespace gets no canon; if asked to write canon there, stop and flag the posture mismatch for the operator.

Read the full file on GitHub · 135 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. 10d ago First seen · 135 lines · 68 tokens per session scan A aa07c8dd0780

Subscribe to this mod's changes

canon-editor is an agent published in the GitHub repository starmynd-org/infinite-brain-os (248 stars, last pushed 14d ago), licensed MIT. It adds 68 tokens to every session and 1,524 once invoked, about $0.0003 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

context-finder

Read-only, memory- and index-aware codebase search. Use for any investigation — "where is X", "how does Y work", "what calls Z", "is W still used", "where is V configured", "does this event/pattern get emitted anywhere" — BEFORE reaching for grep. Consults the knowledge graph, code index, and prior session memory…

futuregerald/futuregerald-claude-plugin · 111 tokens

wiki-ingest

Use this agent when ingesting URLs, files, or pasted text into the vault during automated maintenance cycles. Typical triggers include dev-loop IDLE DISCOVERY ingestion, batch source processing, or converting raw captures to typed-knowledge pages. See "When to invoke" in the agent body for worked scenarios.

karlorz/llm-wiki · 64 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens