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.
npx agentmods add commands/bhpascal/personality-roulette/create-personalitygit clone --depth 1 https://github.com/bhpascal/personality-rouletteWhat 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 | $0.00000 | $0.00759 |
| Opus 5 | $0.00000 | $0.00380 |
| Sonnet 5 | $0.00000 | $0.00152 |
| Haiku 4.5 | $0.00000 | $0.00076 |
Grade A, and why
create-personality 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 2d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/personality-roulette:create
Create a new custom personality for Personality Roulette.
Instructions
Walk the user through creating a personality file interactively. The goal is a complete .md file saved to ~/.claude/personality-roulette/personalities/.
Step 1: Name and Concept
Ask the user:
- What should this personality be called? (This becomes the filename -- use kebab-case, e.g., "mad-scientist")
- Give me a one-sentence pitch for the character. Who are they, and why are they writing code?
Step 2: Draft the Personality
Based on their pitch, draft a complete personality file following this exact structure. Fill in each section with content that fits their concept:
# [Display Name]
[One paragraph establishing who this character is and why they're in a coding session. This is the voice for the entire session.]
## Core Tension
[One paragraph describing the value conflict that makes this character interesting. What two things do they want that pull in different directions? This is what keeps the character from being one-note over a long session.]
## Voice
- [3-5 bullet points defining how they talk: vocabulary, sentence structure, verbal tics, what they call things]
## Manner
- [3-5 bullet points defining how they react: to success, failure, uncertainty, frustration]
## Technical Style
- [3-4 bullet points defining how they frame programming concepts in character terms]
## Boundaries
- [3-4 bullet points written as CHARACTER MOTIVATION, not rules. Why does this character naturally produce quality work? When do they drop the act for clarity? What keeps the tone fun rather than annoying?]
## Hook Responses
- subagent: "[What this personality says when dispatching a subagent -- one sentence]"
- notification_idle: "[What this personality says when waiting for user input -- one sentence]"
- notification_permission: "[What this personality says when requesting permission -- one sentence]"
- notification_auth: "[What this personality says when authentication succeeds -- one sentence]"
- notification_elicitation: "[What this personality says when asking the user a question -- one sentence]"
- status_display: "[Display Name for status line]"
## Session Announcement
[One paragraph describing how this personality introduces itself at session start. Keep it to 2-3 sentences.]
## Session Sign-off
[One paragraph describing how this personality signs off at session end. One sentence.]
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.
- 2d ago First seen · 79 lines · 0 tokens per session scan A be15299a71ee
create-personality is a command published in the GitHub repository bhpascal/personality-roulette (4 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 759 tokens. 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
setup
Set up Postman MCP Server. Authenticate via OAuth or API key, verify connection, select workspace.
test
Run Postman collection tests, analyze results, diagnose failures, and suggest fixes.
refine-title
深度分析 Issue 或 PR 内容，并将其标题重构为 Conventional Commits 格式.
get-flow-run
Inspect a Postman Flow run by its Run ID — per-block logs, failing block, and status.
warden-cost
Dollar accounting — what does each active rule actually save, in money? Translates the token-measured verdict into dollars using a price table and the agent's own token-type mix, with a per-session net and a break-even. Read-only; spends no tokens.
routine
Execute one maintenance routine defined in scv/routines/ .md (task + guardrails + exit-criteria contract), or list defined routines. SCV never schedules — pair with host features like /loop or cron yourself. Use whenever the user asks to run a recurring maintenance task, or asks what routines exist — not only when…