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/handover)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/handover"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/handover.svg" alt="Measured on agentmods" 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 | $0.00029 | $0.01056 |
| Opus 5 | $0.00015 | $0.00528 |
| Sonnet 5 | $0.00006 | $0.00211 |
| Haiku 4.5 | $0.00003 | $0.00106 |
Grade A, and why
handover 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 7d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Handover + Wisdom Capture
Phase 1: Gather Context
Run in parallel:
git log --oneline -15 --decorate
git status --short --branch
git diff --stat origin/main...HEAD
Also check:
- What the user asked for this session (scan conversation for key requests)
- What decisions were made and why
- What surprised you (unexpected complexity, elegant solutions, things that just worked)
Phase 2: Write Handover Doc
Create docs/ops/HANDOVER_{today's date}_{2-word-slug}.md:
# Handover — {date}
## What Landed
{bullet list of commits on main}
## What Changed This Session
{files changed, features added, bugs fixed}
## Current Blockers
{external dependencies, manual steps, unresolved issues}
## Recommended Next Stack
{ordered list of what to work on next, with WHY for each}
## Verification Evidence
{which gates passed, build status, deploy status}
---
## Session Wisdom
### Prompts That Worked
{List the user's most effective prompts this session — what did they ask that produced great results? Quote the prompt pattern, not the full text. These are reusable techniques.}
### Technical Choices Validated
{Decisions made this session that proved right (or wrong). Architecture, library, pattern choices. Include the reasoning — WHY it worked, not just WHAT.}
### Patterns Discovered
{Any repeatable patterns, shortcuts, or approaches worth remembering. Things that would help a future session start faster.}
### What Was Built (Gratitude)
{A brief, genuine reflection on what was accomplished. Not metrics — meaning. What's better about the project now? What creative leaps happened?}
Phase 3: Route to Starlight Vaults
Extract insights from the wisdom section and append to appropriate vaults. Each vault entry is one JSONL line:
{"id":"TYPE_YYYYMMDD_N","insight":"...","category":"...","confidence":"high|medium","source":"session-handover","session":"SLUG","createdAt":"ISO_DATE"}
Route by content:
- Code/architecture/tooling insights →
~/.starlight/vaults/technical.jsonl - Business/product/strategy insights →
~/.starlight/vaults/strategic.jsonl - Design/style/voice insights →
~/.starlight/vaults/creative.jsonl - Workflow/process/ops insights →
~/.starlight/vaults/operational.jsonl - Cross-domain meta-patterns →
~/.starlight/vaults/wisdom.jsonl(create if missing) - Benevolent human-AI collaboration insights →
~/.starlight/vaults/horizon.jsonl
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.
- 7d ago First seen · 119 lines · 29 tokens per session scan A 923de03489e9
handover is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 1,056 once invoked, about $0.0001 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.