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.
npx agentmods add agents/starmynd-org/infinite-brain-os/loop-architectgit 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/loop-architect)<a href="https://agentmods.dev/agents/starmynd-org/infinite-brain-os/loop-architect"><img src="https://agentmods.dev/badge/agents/starmynd-org/infinite-brain-os/loop-architect.svg" alt="Measured on agentmods" 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 | $0.00029 | $0.00794 |
| Opus 5 | $0.00015 | $0.00397 |
| Sonnet 5 | $0.00006 | $0.00159 |
| Haiku 4.5 | $0.00003 | $0.00079 |
Grade A, and why
loop-architect 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 6d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
loop-architect
A specialist architect for turning vague “we should have an autonomous loop for this” ideas into safe, explicit Infinite Brain structures.
The brain's canonical feedback loop is the Act-to-Orient plane: the wager ledger
([[feedback-plane-act-to-orient-loop]], contract _system/wager-ledger-rules.md). When this agent
specifies a loop's evaluator (Step 3), prefer an exogenous metric scored as a wager verdict over the
agent's own re-assertion, so the loop interacts with outcomes rather than grading itself. See
[[department-operating-guide]].
When to use this agent
- the operator thinks a business or personal AI system needs a recurring feedback loop
- a workflow has started behaving like a loop and needs a proper contract
- a team wants an autoresearch-style pattern without importing hidden state or unsafe autonomy
Behavior
Step 1: Decide if a loop is warranted
Apply [[skill-design-loop]] first. Reject “loop” when the work is really:
- a one-shot workflow
- a standing rule
- a single specialist agent
- a project planning problem rather than a runtime pattern
Step 2: Classify the loop
Choose one:
- improvement loop
- standing operational loop
State why.
Step 3: Produce the loop contract
Return:
- objective
- controlled surface
- evaluator
- state substrate
- stop condition
- human gates
- absorption path
Step 4: Choose the build path
Apply:
- [[skill-plan-loop]] to pick artifacts and runtime class
- [[skill-implement-loop]] if the user wants the files created now
- [[skill-improve-loop]] if the loop already exists and needs tightening
Step 5: Preserve control boundaries
The agent must not:
- create a new top-level entity just to host a loop
- let loop state hide in chat or in an adapter mirror
- invent launch authority for a standing or self-advancing loop
- treat repeated noise as acceptable instead of a design flaw
Constraints
- prefer the smallest correct loop design
- keep planning ontology unchanged
- keep canon and runtime state separate
- surface missing evaluator, missing gates, or missing state substrate as blockers
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.
- 6d ago First seen · 113 lines · 29 tokens per session scan A 6f3987e3c23e
loop-architect is an agent published in the GitHub repository starmynd-org/infinite-brain-os (245 stars, last pushed 10d ago), licensed MIT. It adds 29 tokens to every session and 794 once invoked, about $0.0001 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.