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/hire-icp)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/hire-icp"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/hire-icp/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/hire-icp"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/hire-icp.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 | $0.02676 |
| Opus 5 | $0.00038 | $0.01338 |
| Sonnet 5 | $0.00015 | $0.00535 |
| Haiku 4.5 | $0.00008 | $0.00268 |
Grade A, and why
hire-icp 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 11d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/hire-icp
This is part of the People Intelligence reference vertical. Composes with Genius Profile + Vision/Brand for company-as-candidate framing.
Load SIP.md, VOICES.md, agents/starlight-hiring.md, skills/people-intelligence/structured-hiring.md, and if present the company's Genius Profile (genius/profile-<company-slug>.md) and Vision Architecture (vision/vision-<company-slug>.md). Produce an Ideal Candidate Profile for the named role. Hand off to exactly one next command.
Disclaimer (non-waivable)
Hiring decisions touch employment law and protected-class considerations. This is system architecture, not legal advice. Validate jurisdiction-specific compliance with qualified counsel before publishing the role description or running interviews.
This command organizes thinking before you write the JD or run the loop. It does not replace legal review. It does not replace your recruiter. It produces a calibrated profile so the loop is precise and the debrief is rubric-anchored.
Input
$ARGUMENTS
Flags
--jurisdiction <US-state|EU-country|UK|other>— primary jurisdiction the role operates in. Affects compliance flag (e.g., NYC pay-transparency, CA salary-history bans, EU GDPR for candidate data, UK right-to-work). If multi-jurisdictional, pass primary and flag in context paragraph.--team-size <n>— current team size. Drives culture-add gap analysis (a 5-person team vs. 50-person team has very different gap profiles).--stage <pre-seed|seed|series-a|series-b+|established>— company stage. Drives ramp-time tolerance, ambiguity tolerance, and breadth-vs-depth weighting in the ICP.
Process
-
Disclaim. Open the output with the non-waivable disclaimer. Structurally first.
-
Locate. Confirm role title, jurisdiction, team size, stage. Confirm whether Genius Profile and Vision Architecture exist for the company. If not, flag — but do not block.
-
Read. If Genius Profile exists, note the company's voice signature (will inform candidate-facing materials downstream). If Vision Architecture exists, note 3-year and 10-year horizons (will inform "what is this team building?" framing in outreach).
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.
- 11d ago First seen · 191 lines · 76 tokens per session scan A 18d1cf9cc766
hire-icp 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 2,676 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.