Borrowing it
Nothing to install: this file belongs to frankxai/Starlight-Intelligence-System. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/frankxai/Starlight-Intelligence-System/main/.claude/commands/perf-coaching-protocol.mdgit 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-coaching-protocol)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/perf-coaching-protocol"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/perf-coaching-protocol.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 | $0.00083 | $0.03947 |
| Opus 5 | $0.00042 | $0.01973 |
| Sonnet 5 | $0.00017 | $0.00789 |
| Haiku 4.5 | $0.00008 | $0.00395 |
Grade A, and why
perf-coaching-protocol 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 8d 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 — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/perf-coaching-protocol
Load SIP.md, VOICES.md, agents/starlight-performance.md, skills/people-intelligence/feedback-conversations.md, and the coach's Genius Profile if available. Produce a Coaching Session Protocol — a 60-minute session structure the manager will use, plus follow-up prompts and the manager-as-coach training notes. Save to people-intelligence/performance/coaching-<coachee-slug>-<YYYY-MM-DD>.md.
Disclaimer (non-waivable)
This is a performance coaching protocol grounded in Solution-Focused Brief Therapy (de Shazer, Berg) and CBT-aligned framing. It is NOT psychotherapy. If the coachee surfaces clinical-level distress — suicidality, untreated trauma, active eating disorder, substance use crisis, severe depression that is not lifting, panic attacks, or any symptom that suggests a clinical boundary — stop the coaching engagement and route to qualified clinical support. Coaching that crosses into psychotherapy harms the coachee and exposes the organization. The manager-as-coach is a coach, not a therapist.
Input
$ARGUMENTS
When this command fires
- A manager has a recurring 1:1 with a report and the conversation has been performative — the report walks in, the manager asks "how's it going", the report says "fine", thirty minutes evaporate
- A manager has identified a stuck point in the report's work and wants to help the report think through it without giving the answer
- A new manager has been told "you should coach your team" and has no protocol for what that actually means
- The report has asked for coaching — proactively raising a development goal or a stuck point
When this command does NOT fire
- The session is a feedback session (specific behavior needs to be named) → route to
/perf-feedback-rehearsal - The session is a difficult conversation (termination, demotion, hard feedback) → route to
/perf-difficult-conversation - The coachee is in clinical-level distress → refuse and route to clinical support
- The manager wants the script to "tell them what to do" → refuse; coaching uses questions, not advice. If advice is the goal, the conversation is mentoring or directing, not coaching, and a different protocol applies
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.
- 8d ago First seen · 291 lines · 83 tokens per session scan A 75871d77fcdb
perf-coaching-protocol is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 83 tokens to every session and 3,947 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.