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.
curl -O https://raw.githubusercontent.com/starmynd-org/infinite-brain-os/main/.claude/agents/corpus-synthesizer.mdgit clone --depth 1 https://github.com/starmynd-org/infinite-brain-osWrote 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/starmynd-org/infinite-brain-os/corpus-synthesizer)<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.
<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>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 | $0.00077 | $0.01499 |
| Opus 5.5 | $0.00031 | $0.00600 |
| Sonnet 5.5 | $0.00015 | $0.00300 |
| Haiku 4.5 | $0.00008 | $0.00150 |
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 2mo 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.
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
garytanfeeds intoai-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.
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.
- 2mo ago First seen · 134 lines · 77 tokens per session scan A c632a312378d
corpus-synthesizer is an agent published in the GitHub repository starmynd-org/infinite-brain-os (273 stars, last pushed 17d ago), licensed MIT. It adds 77 tokens to every session and 1,499 once invoked, about $0.0003 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.
corpus-synthesizer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| corpus-synthesizerstarmynd-org/infinite-brain-os | Agent | 273 | 17d ago | MIT | A | 77 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | yesterday | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | 4d ago | MIT | A | 33 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 2d ago | MIT | A | 52 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 61 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 11 | Claude Code |
| WinForms Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 19 | Claude Code |