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-assess-fit)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/hire-assess-fit"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/hire-assess-fit/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-assess-fit"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/hire-assess-fit.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 | $0.02437 |
| Opus 5 | $0.00038 | $0.01218 |
| Sonnet 5 | $0.00015 | $0.00487 |
| Haiku 4.5 | $0.00008 | $0.00244 |
Grade A, and why
hire-assess-fit 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/hire-assess-fit
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, the ICP (people-intelligence/hiring/icp-<role-slug>-*.md), and the interview debrief if it exists. Produce a Culture-Add Fit Assessment. Hand off to debrief or hire decision.
Disclaimer (non-waivable)
Hiring decisions touch employment law and protected-class considerations. Culture-add assessment must NOT proxy for protected-class characteristics — race, gender, age, religion, national origin, disability, family status. This is system architecture, not legal advice. Validate jurisdiction-specific compliance with qualified counsel.
This command is a supplement to the structured rubric, not a replacement. If "fit" is being used to override a strong rubric score, the bias to flag is similarity-attraction, not the candidate. The fit assessment is read-after-rubric, never read-instead-of-rubric.
Input
$ARGUMENTS
Process
-
Disclaim. Open with the non-waivable disclaimer. Add explicit warning: culture-add must not proxy for protected-class.
-
Locate. Confirm candidate-slug and role-slug. Read the ICP. Read the team-state from Operational vault if available (current team composition, skills, perspectives, energy patterns).
-
Refuse generic framing. If the impulse is "great culture fit" or "we just clicked," halt. The fit assessment does not produce vibes; it produces gap-bridge analysis. If the candidate generates only "we clicked" signal, that signal is similarity-attraction. Name it and continue.
-
Team-as-of-now snapshot. What does the team currently have? Skills, perspectives, energy types, lived-experiences. Be specific. ("The team has 4 deep-domain ICs and 1 cross-functional generalist; energy is heads-down execution; lived experience is largely scaling-stage startups.")
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 · 169 lines · 76 tokens per session scan A 137f43becae0
hire-assess-fit 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 2,437 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.