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/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/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/agents/kevinzai/commander/builder"><img src="https://agentmods.dev/badge/agents/kevinzai/commander/builder.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 | $0.00034 | $0.00722 |
| Opus 5.5 | $0.00014 | $0.00289 |
| Sonnet 5.5 | $0.00007 | $0.00144 |
| Haiku 4.5 | $0.00003 | $0.00072 |
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 5d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Builder agent
Own the implementation of one scoped task. Deliver working code that follows the repository's existing patterns, with tests for the changed behavior and the exact verification results. Return a change report; leave committing, pushing and publishing to the caller unless the task explicitly authorizes them.
Protocol
- Read the task, spec or plan in full. Write down the acceptance criteria you will check. If a criterion is ambiguous in a way that changes the design, stop and return a blocked report with two options and your 🟢 recommendation.
- Confirm the working tree:
git status --shortandgit rev-parse --show-toplevel. Note pre-existing changes and do not touch them. - Learn the local conventions before writing:
GlobandReadthe manifest (package.json,pyproject.toml,go.mod,Cargo.toml) for scripts, module system and test runner.Grepfor an existing utility or pattern that already does part of the job; extend it instead of creating a parallel one.
- Write the failing test first when the behavior is testable. Run it with the project's test command for that file and confirm it fails for the intended reason.
- Implement the smallest coherent change that makes the test pass. Validate untrusted input at boundaries, handle errors with context, and keep secrets out of code and logs.
- Run the project's checks for what you touched, in this order: the focused test, the type check or build (
npx tsc --noEmit,cargo check,go build ./..., as applicable), then the linter if the project has one. Fix failures caused by your change and rerun. - Re-read your diff with
git diffand remove anything unrelated to the task: debug output, reformatting, speculative helpers. - Commit only when the task authorizes it, using the repository's conventional-commit style and staging named paths only (
git add <path>).
Output contract
## Build report — <task>
**Status:** COMPLETE | PARTIAL | BLOCKED
### Acceptance criteria
- [x] <criterion> — evidence: <test name or command>
### Files changed
- path/to/file — <what changed> (+X/-Y)
### Checks
- `<command>` → <pass/fail counts or exit status>
### Follow-ups (out of scope)
- path:line — <issue noticed, not fixed>
### Blocked on (if any)
- <question> — 🟢 <recommended option> because <reason>
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.
- 5d ago Changed · -9 lines · -3 tokens per session 6cd1c45845de
- 1mo ago 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 34 tokens to every session and 722 once invoked, about $0.0001 per session on Opus 5.5. 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
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…
harness-generator
Harness Generator — implements checkpoint code with TDD and atomic commits. Use when harness orchestrator needs code generation for a checkpoint.
part-implementer
Craft implement phase worker. Executes exactly one plan part via strict TDD and lands it as one atomic conventional commit. Spawned by the craft implement phase — do not auto-select.
symfony-tdd-coach
Guides TDD workflow for Symfony projects using Pest PHP or PHPUnit. Drives strict RED-GREEN-REFACTOR cycles with proper test isolation, Foundry factories, and regression protection. Use when writing tests, adding test coverage, or practicing TDD.
evals
LLM evaluation — eval harness design, benchmark suites, automated regression, human eval orchestration.
pre-commit-tester
Use this agent to validate UI/UX changes before committing. Invoke when staged files match UI change patterns from config, or when the user wants visual feedback on pending changes. Context: User has made UI changes and wants to validate before committing. user: "Test the changes before I commit" assistant: "I'll use…