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.
git 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/design-regimen)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/design-regimen"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/design-regimen/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/commands/frankxai/starlight-intelligence-system/design-regimen"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/design-regimen.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 | $0.00060 | $0.03109 |
| Opus 5 | $0.00030 | $0.01554 |
| Sonnet 5 | $0.00012 | $0.00622 |
| Haiku 4.5 | $0.00006 | $0.00311 |
Grade A, and why
design-regimen 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 9d 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/design-regimen
Load SIP.md, VOICES.md, agents/starlight-embodiment.md, skills/health/body-substrate.md, skills/health/energy-architecture.md. Invoke gym-training-expert and health-nutrition-expert skills for domain specifics. Produce a Regimen Architecture — weekly template integrating training + nutrition + sleep + stress + recovery. Save to health/regimen-<person-slug>.md.
Input
$ARGUMENTS
When this command fires
- A person wants a coherent regimen across training, nutrition, sleep, stress, and recovery.
- They want their physical substrate to support creative and intellectual output, not fight it.
- They want long-game architecture, not a 90-day transformation program.
- A
/energy-audithas been completed (strongly preferred) and the map is available.
When this command does NOT fire
- User has an active medical condition, injury, or clinician-supervised protocol that requires medical guidance → halt and defer.
- User wants single-domain advice (training only, nutrition only) → route directly to
gym-training-expertorhealth-nutrition-expert. - User wants fad protocol (keto-only without indication, under-4h sleep, extreme IF) → refuse and explain why.
Process
-
Resolve inputs.
<person-slug>from<person-name>(kebab-case).- Parse optional
--audit,--genius,--life-stageflags. - If
--auditnot provided, check forhealth/audit-<person-slug>-*.md. If no audit exists, halt with:Run /energy-audit <person> first — a regimen without an energy map is guessing. Seven-day log beats seven-minute vibes. - If
--geniusnot provided, check forgenius/profile-<person-slug>.md. Load if present (to align regimen to creative peaks). Proceed without if absent — note that creative-peak alignment is approximate. - Default
--life-stageto the level implied by the audit, or ask the person if ambiguous.
-
Read the audit.
- Extract: peak windows across five dimensions, crash windows, named leaks, ranked fixes.
- If audit is older than 90 days, halt with:
Audit is stale. Run /energy-audit <person> again before designing — life has moved.
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.
- 9d ago First seen · 209 lines · 60 tokens per session scan A e27f89d0e18e
design-regimen is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 3,109 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 2026-08-31.
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.