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/energy-audit)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/energy-audit"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/energy-audit/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/energy-audit"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/energy-audit.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 | $0.00056 | $0.02871 |
| Opus 5 | $0.00028 | $0.01435 |
| Sonnet 5 | $0.00011 | $0.00574 |
| Haiku 4.5 | $0.00006 | $0.00287 |
Grade A, and why
energy-audit 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.
How it starts
The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/energy-audit
Load SIP.md, VOICES.md, agents/starlight-embodiment.md, skills/health/energy-architecture.md. Run a seven-day energy self-audit across five dimensions. Produce pattern analysis, leak identification, and ranked fixes. Save to health/audit-<person-slug>-<YYYY-MM-DD>.md.
Input
$ARGUMENTS
When this command fires
- A person reports energy crashes, burnout, unsustainable output, or inability to sustain creative work.
- Before
/design-regimen— a regimen without an energy map is guessing. - Quarterly re-baseline of an existing regimen.
- After a major life-structure change (new job, caregiving shift, move, relationship change, long illness, major launch recovery).
When this command does NOT fire
- User reports persistent fatigue with medical red flags (unexplained weight loss, chronic pain, symptoms surviving regimen correction) → defer to clinician.
- User wants a one-off sleep tip or single-domain optimization → route to the specific skill.
- User won't commit to a seven-day log → return the "empirical over narrative" halt message at Step 1.
Process
-
Determine mode.
--start-log→ scaffold a blank 7-day log template for the person to fill in over the next week. Save tohealth/log-<slug>-<start-date>.md. Return the log path and instructions. End here. Audit continues when the person returns with the filled log.--log <path>→ load the completed log and proceed.--retroactive→ the person has not kept a log but can reconstruct a typical week from memory. Accept with a caveat: retroactive audits are ~60% as reliable as a live log. Proceed but flag the reduced confidence in the output.- No flag and no log → return:
Energy audit needs a seven-day log. Run "/energy-audit <person> --start-log" to scaffold, fill in over the next week, then run "/energy-audit <person> --log <path>" to analyze. If you can reconstruct a typical week from memory, pass --retroactive instead.
-
Safety gate (non-medical deferral check).
- Scan provided context for mentions of: chronic pain, persistent fatigue surviving sleep correction, unexplained weight loss, suspected eating disorder, active depression symptoms, current clinician-supervised protocol.
- If any appear, return:
Your context includes <flag>. Energy self-audit is not a substitute for clinician evaluation. Confirm with your clinician first, then we can run this as a supplementary self-audit around their care.
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.
- 10d ago First seen · 226 lines · 56 tokens per session scan A 6cef3b3bb972
energy-audit is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 2,871 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
agent
Create and manage custom AI agents.
memories
View and manage learned memories.
mpm-session-resume
Load context from paused session.
forget
Delete specific memories.
learn
Add new learning to memory.
learn
End-of-session learning loop — analyze signals, approve instincts, capture directives, refresh MEMORY.md. Invokes dreamteam learn; one source of behavioral truth shared with the team.md SESSION LEARNING step.