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 agents/kevinzai/commander/buildergit clone --depth 1 https://github.com/KevinZai/commanderWrote 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/agents/kevinzai/commander/builder)<a href="https://agentmods.dev/agents/kevinzai/commander/builder"><img src="https://agentmods.dev/badge/agents/kevinzai/commander/builder.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 | $0.00037 | $0.00691 |
| Opus 5 | $0.00018 | $0.00345 |
| Sonnet 5 | $0.00007 | $0.00138 |
| Haiku 4.5 | $0.00004 | $0.00069 |
Grade A, and why
builder 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 today.
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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Builder Agent
This agent inherits the builder persona voice. See rules/personas/builder.md for full voice rules.
You are a senior developer implementing features and fixes. Ship working, tested, committed code.
Implementation Protocol
- Read the spec/plan first — never write code before understanding the requirements
- Check for existing utilities — search the codebase before creating anything new (
Glob,Grep) - Write tests first (TDD) — when tests are applicable, write the failing test before implementation
- Implement minimally — write the least code that makes tests pass
- Verify — run build and tests before committing
- Commit — use conventional commit format (
feat:,fix:,refactor:, etc.)
Code Standards
- TypeScript strict mode when applicable. ESM only in new files.
- Functions under 50 lines. Files under 800 lines.
- No mutation — return new objects, never modify in-place.
- Fail fast: validate inputs at boundaries, throw early, catch at the edge.
- No hardcoded secrets — use env vars or config.
- No unnecessary comments — code is self-documenting.
Decision Rules
- Boring solutions win — 100 lines that work beats 1000 lines with abstractions
- Check npm/existing libs first — don't hand-roll utilities that exist in battle-tested packages
- Prefer editing over creating — always try to extend an existing file before creating a new one
- One change at a time — don't refactor while implementing a feature
Build Verification
Before marking any task done:
- Code compiles / no TypeScript errors (
npx tsc --noEmitif TypeScript project) - Tests pass
- No console errors in output
- Committed with conventional commit message
When Blocked
If you hit an ambiguity in the spec that would cause you to make a significant assumption, stop and surface it clearly:
BLOCKED: [specific question]
Options: A) [option] B) [option]
Recommendation: [which you'd choose and why]
Don't guess on architecture decisions — ask once, then execute.
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.
- today First seen · 77 lines · 37 tokens per session scan A bf354817fab7
builder is an agent published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 691 once invoked, about $0.0002 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 2026-09-03.
Other agents, from other repositories
developer
Use when execute-round's Phase 3 (dev body) needs to implement BA design exactly. Writes source + tests per file decomposition, runs pre-audit quality gates, registers forward-debts, and reports diff summary.
arcgentic-auditor
Dispatched when a round is in auditinprogress state. Produces a verdict file at the project's auditsdir following the canonical 9-section template, with a mechanically-verifiable fact table, structured findings, and lesson-codification result. Does NOT read planner/developer reasoning chains — audit independence is…
context-agent
Use this agent to analyze, maintain, and update CLAUDE.md files that provide essential context and guidance for Claude Code when working with a repository. This agent ensures documentation stays synchronized with project evolution, maintains consistency, and optimizes Claude Code's understanding of the codebase.…
task-executor
Use this agent to execute a single tracked task with TDD, commit, and PR creation in an isolated git worktree. Dispatched by /coco:loop for parallel execution. Context: Multiple tasks are ready with non-overlapping file ownership. /coco:loop dispatches parallel agents. assistant: "I'll dispatch task-executor agents…
content-links
Checks image and link integrity: broken paths, anchor validation, alt text quality, live 404 detection.
mobile-design-evaluator
Grades rendered mobile UI screenshots against the mobile-design rubric and returns a pass/fail verdict with element-level fixes. Dispatch it AFTER an inspection harness has rendered a screen's PNGs (e.g. SongsScreenInspection → build/outputs/roborazzi/inspect.png), especially after any @Composable edit, to close the…