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/culture-design)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/culture-design"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/culture-design/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/culture-design"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/culture-design.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 | $0.00076 | $0.02466 |
| Opus 5 | $0.00038 | $0.01233 |
| Sonnet 5 | $0.00015 | $0.00493 |
| Haiku 4.5 | $0.00008 | $0.00247 |
Grade A, and why
culture-design 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 12d 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/culture-design
Load SIP.md, VOICES.md, agents/starlight-culture.md, skills/people-intelligence/culture-design.md. Produce a Culture Audit & Redesign Plan. Hand off to exactly one next move.
Refusal frame (non-waivable)
This command does not produce values posters, off-site agendas, or one-off culture initiatives. Culture is a system; this command audits the system and recommends systems-redesign. If the request is "give us three values for the wall," surface that this is not culture work and route to systems-redesign.
Input
$ARGUMENTS
Flags
--size <S|M|L>— S = under 50 people, M = 50-250, L = 250+. Sequencing changes by org size.--declared-values "v1,v2,v3"— the 3-5 declared values from the values poster, deck, or about page. Required.--pain "pain1; pain2"— observed pain points (high attrition, low engagement, political behavior, etc.). At least one required.- Optional context paragraph — recent events (M&A, restructure, founder transition), industry, remote/hybrid/onsite mix.
Process
- Refuse poster work. If the request is values-selection-only, halt and route to operational systems-redesign.
- Audit current state — for each declared value, surface what's rewarded / punished / ignored with observable evidence. Schein three-layer (artifacts → espoused → underlying assumptions).
- Gap analysis — name the divergence between declared values and lived behavior, specifically, with evidence.
- Systems redesign by leverage — for each value to be made real, surface which of the six systems (hire / promote / celebrate / fire / measure / pay) must change. Sequence by leverage; promotion criteria typically rank highest.
- 12-week implementation sequence — concrete, week-numbered, owned actions. Not a 5-year strategy. The 12-week window forces sequencing discipline.
- Save — write to
people-intelligence/culture/audit-redesign-<org>-<date>.md. - Hand off — exactly one named next move (default:
/culture-values-opsto operationalize the top value first).
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.
- 12d ago First seen · 208 lines · 76 tokens per session scan A 82a291037203
culture-design is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 76 tokens to every session and 2,466 once invoked, about $0.0004 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.