sema: Command for Claude Code

.claude/commands/swarm-personas.md

swarm-personas is a command for Claude Code from sema-lisp/sema. It costs 0 tokens per session (1,587 once invoked), scanned A, original, MIT.

A command that asks several programming-language designers' documented viewpoints to analyze a software design question and reach a consensus.

In plain words
What is it for?
Use it for design decisions involving programming-language syntax, meaning, implementation, or developer experience.
Why use it?
It exposes disagreements and tradeoffs that a single generic review might miss.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is sema-lisp/sema's own configuration. It tells Claude Code how to work on sema itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sema configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sema-lisp/sema. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sema-lisp/sema/main/.claude/commands/swarm-personas.md
Clone the repo
git clone --depth 1 https://github.com/sema-lisp/sema

Made for: Claude Code.

Wrote 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.

agentmods badge for swarm-personas

README.md
[![agentmods](https://agentmods.dev/badge/commands/sema-lisp/sema/swarm-personas/github.svg)](https://agentmods.dev/commands/sema-lisp/sema/swarm-personas)
Your own site
<a href="https://agentmods.dev/commands/sema-lisp/sema/swarm-personas"><img src="https://agentmods.dev/badge/commands/sema-lisp/sema/swarm-personas/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.

agentmods 80×15 button for swarm-personas

Your own site · 80×15
<a href="https://agentmods.dev/commands/sema-lisp/sema/swarm-personas"><img src="https://agentmods.dev/badge/commands/sema-lisp/sema/swarm-personas.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,587 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01587
Opus 5 $0.00000 $0.00794
Sonnet 5 $0.00000 $0.00317
Haiku 4.5 $0.00000 $0.00159

Measured 10d ago against content hash 79d12fcb3a1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

swarm-personas 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 10d 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.

.claude/commands/swarm-personas.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Swarm Consensus — PL Designer Personas

You are orchestrating a multi-agent consensus analysis using the perspectives of real programming language designers. Each agent argues from that person's documented philosophy — not a generic lens.

Step 1 — Determine N from complexity

Assess the problem:

  • Scope: Narrow tactical or broad strategic?
  • Ambiguity: Clear answer or values/tradeoffs?
  • Stakes: How costly is a wrong decision?
  • Domain breadth: Does it touch syntax, semantics, implementation, and user experience?

Pick N:

Complexity N When
Low 3 Single concern, clear tradeoffs, reversible
Medium 5 Multi-factor, some ambiguity, moderate stakes
High 7 Cross-cutting design, high ambiguity, hard to reverse
Critical 10 Strategic direction, high stakes, deeply uncertain

State your chosen N and why before spawning.


Step 2 — Select personas and spawn N agents in parallel

Choose N personas from this cabinet. Pick personas that will genuinely disagree on the problem at hand — don't select 5 people who'll say the same thing. Use the conflict matrix below to ensure productive tension.

The Cabinet

# Persona Core Philosophy Best For
1 Guy Steele Languages must be designed to grow. User extensibility is non-negotiable. Parallelism is the future. Module systems, extensibility, macro design, language evolution
2 Gerald Sussman Pragmatic formalism. Empirical testing beats theoretical purity. Side effects are real — design around them. Evaluation strategy, teaching implications, closure/scope design
3 Rich Hickey Simple != easy. State, identity, and value are separate concerns. Immutable data composes; mutable state entangles. Data vs. behavior, state management, API surface design
4 Paul Graham Lisp's power is code=data and macros reshaping the language. Linguistic flexibility is competitive advantage. Macro systems, syntax choices, metaprogramming, s-expression design
5 Rob Pike Less is exponentially more. Orthogonal composable features. Comprehensibility over cleverness. Resist feature creep. Feature set scope, API minimalism, when to say no
6 Joe Armstrong Design around failure, not against it. Isolation and message-passing. Let it crash, supervise, restart. Error handling, concurrency, agent architecture, fault tolerance
7 Simon Peyton Jones Purity enables reasoning. Side effects should be explicit and trackable. Types catch bugs at compile time. Type system questions, effect tracking, evaluation order, correctness
8 Matthew Flatt Modules enable DSLs. Phase separation (compile vs. runtime) is crucial. Languages are libraries. Module system, DSL embedding, phase-aware macro systems
9 Roberto Ierusalimschy Mechanisms not policies. Small core, embed everywhere. Interop is the killer feature. Tables are enough. Embedding API, minimal core design, interop boundaries, VM design
10 Bob Nystrom Show the implementation. Every concept should be explainable via concrete code. No black-box magic. VM/interpreter design, documentation, implementation clarity
11 Kent Pitman Community shapes languages. Codify working practice, don't impose ideals. Conditions > exceptions. Error handling, stdlib conventions, community/ecosystem decisions
12 Brendan Eich Good design under real constraints beats perfect design. First-class functions enable everything. Pragmatic trade-offs, mixed-paradigm design, shipping under pressure
13 Peter Norvig Data over formalism. Leverage statistics and scale. Paradigms of AI programming. LLM integration design, AI-native features, practical AI patterns
14 Guido van Rossum Readability is social. One obvious way. Consistency and least surprise matter more than minimal syntax. Developer experience, error messages, API naming, onboarding

Read the full file on GitHub · 136 lines

Changes

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.

  1. 10d ago First seen · 136 lines · 0 tokens per session scan A 79d12fcb3a1e

Subscribe to this mod's changes

swarm-personas is a command published in the GitHub repository sema-lisp/sema (41 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,587 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 2026-08-30.