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/perf-conflict-mediation)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/perf-conflict-mediation"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/perf-conflict-mediation/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/perf-conflict-mediation"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/perf-conflict-mediation.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 | $0.00095 | $0.04437 |
| Opus 5 | $0.00048 | $0.02218 |
| Sonnet 5 | $0.00019 | $0.00887 |
| Haiku 4.5 | $0.00010 | $0.00444 |
Grade A, and why
perf-conflict-mediation 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 — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/perf-conflict-mediation
Load SIP.md, VOICES.md, agents/starlight-performance.md, skills/people-intelligence/feedback-conversations.md. Produce a Conflict Mediation Plan — separate prep sessions with each party (each producing a three-conversations narrative privately) + joint 90-minute session structure + commitments framework + follow-up plan + escalation criteria. Save to people-intelligence/performance/mediation-<conflict-slug>-<YYYY-MM-DD>.md.
Disclaimer (non-waivable)
This is psychologist-grade mediation rehearsal architecture for ordinary workplace conflict between two parties of comparable positional power. It is NOT:
- Legal counsel. If the conflict involves potential legal claims, employment law applies — engage counsel.
- Professional mediation. Some conflicts exceed in-house capability and require an external certified mediator (CEDR, IMI, FMCS, or jurisdiction-equivalent). Boundaries below.
- Investigation. If the conflict involves allegations of harassment, discrimination, retaliation, or other misconduct, mediation is the WRONG tool. Investigation is the right tool. Halt and route to legal + HR.
- Therapy. If the conflict is substantially driven by clinical-level distress in either party, route to clinical support before/instead.
This rehearsal refuses to mediate:
- Harassment (sexual, racial, religious, disability-based, or any protected-class harassment)
- Discrimination (any protected-class discrimination claim)
- Retaliation (any post-protected-activity retaliation claim)
- Substantial-power-imbalance conflicts (e.g., a director and an IC who reports up the same chain; a partner and a junior; any case where one party has authority over the other in the disputed dynamic)
- Conflicts where one party is in clinical-level distress that the conflict is feeding
For these, halt and route to legal + HR + investigation. Mediating these is exposure for the company and harm for the parties.
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 · 321 lines · 95 tokens per session scan A 0ff9824eaadb
perf-conflict-mediation is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 95 tokens to every session and 4,437 once invoked, about $0.0005 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.