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 commands/frankxai/starlight-intelligence-system/agent-creatorgit clone --depth 1 https://github.com/frankxai/Starlight-Intelligence-SystemWrote 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/commands/frankxai/starlight-intelligence-system/agent-creator)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/agent-creator"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/agent-creator.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 | $0.00046 | $0.00497 |
| Opus 5 | $0.00023 | $0.00249 |
| Sonnet 5 | $0.00009 | $0.00099 |
| Haiku 4.5 | $0.00005 | $0.00050 |
Grade A, and why
agent-creator 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.
What it actually says
/agent-creator
Generate a new agent profile markdown file, register it in the canonical registries, and verify that the symmetry checks remain green.
Parameters
<agent-name>: Name of the agent (e.g.,marine-acoustics,space-orbit).--domain: Core domain slug (e.g.,marine-intelligence,space-cosmos,longevity).--voice: Voice profile fromVOICES.md(e.g.,specialist,architect,synthesizer).--skills: Comma-separated list of initial active skills.--path: Optional target folder path (for writing to a modular sub-repository directory, defaulting toagents/).
Execution Steps
- Format Verification: Ensures the agent name matches lowercase + hyphen syntax (
[a-z][a-z0-9-]*). - Duplicate Check: Scans
AGENTS.mdandagents/directory to prevent naming collisions. If a collision is found, suggests suffix and prompts. - Template Generation: Scaffolds the markdown file using the canonical agent template, injecting YAML frontmatter (name, tier, domain, voice), mission statement, active skills, reasoning protocols, and quality gates.
- Registry Append: Appends the agent metadata row and file link to
agents/AGENT_REGISTRY.mdand rootAGENTS.md. - Validation Check: Automatically executes
tsc --noEmitandnpm test test/v76.test.tsto ensure agent registry symmetry is preserved.
Built on the sovereign substrate of the Starlight Intelligence Protocol (SIP v1.1.1)
- Substrate: starlightintelligence.org/protocol v1.1.1
- Layers: [file-contract, attestation, sovereignty, agent-registry]
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 · 33 lines · 46 tokens per session scan A 038ae0c4702d
agent-creator is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 497 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.
Other commands, from other repositories
memories
View and manage learned memories.
mpm-session-resume
Load context from paused session.
forget
Delete specific memories.
learn
Add new learning to memory.
gbu-retro
Post-session retrospective — harvest this session's lessons into durable doctrine.
consolidate
Write a compact checkpoint summary of the current frontier.