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/commands/kevinzai/commander/ccc-feature-start)<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-feature-start"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-feature-start/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/commands/kevinzai/commander/ccc-feature-start"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-feature-start.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 | $0.00044 | $0.01043 |
| Opus 5.5 | $0.00018 | $0.00417 |
| Sonnet 5.5 | $0.00009 | $0.00209 |
| Haiku 4.5 | $0.00004 | $0.00104 |
Grade A, and why
ccc-feature-start 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 7d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ccc-feature-start — structured feature kickoff
CC Commander · /ccc-feature-start · a feature branch, a passing baseline, tasks/todo.md, and a first failing test.
Feature: $ARGUMENTS. If empty, ask for a one-line feature name in plain text. Derive <slug> as lowercase kebab-case of the name.
What happens
1. Research and context
- Search the codebase for related code with
rg -n "<key terms>"; list matching files. - If
ghis available and authenticated, rungh pr list --search "<key terms>" --state all --limit 10andgh issue list --search "<key terms>" --limit 10. - If
tasks/lessons.mdexists, read it and note lessons that apply. - Identify the files, modules and APIs this feature touches and where it belongs in the architecture.
2. Branch and setup
- Run
git status --porcelain. If the tree is dirty, show the changes and stop until the user decides how to handle them; never stash or discard them yourself. - Find the base branch:
git symbolic-ref --short refs/remotes/origin/HEAD(falls back tomain). Rungit fetch origin <base>. - Ask with AskUserQuestion (plain-text question where unavailable):
- 🟢 New worktree —
git worktree add ../<repo>-<slug> -b feature/<slug> origin/<base>; the current checkout stays untouched. - Branch in this checkout —
git checkout -b feature/<slug> origin/<base>.
- 🟢 New worktree —
- Verify:
git rev-parse --abbrev-ref HEADprintsfeature/<slug>(run inside the worktree when one was created). - Run the baseline tests with the project's command: the
testscript inpackage.json(npm test),pytest,go test ./..., orcargo test. Record PASS or FAIL. On FAIL, report the failing tests and ask whether to continue; a red baseline makes later results ambiguous.
3. Task breakdown
Write tasks/todo.md (append a new section if the file exists):
# Feature: <feature name>
## Tasks
- [ ] Write spec (requirements, acceptance criteria, edge cases)
- [ ] Design API/interface (if applicable)
- [ ] Write failing tests (TDD red phase)
- [ ] Implement core logic (TDD green phase)
- [ ] Refactor and clean up
- [ ] Integration tests
- [ ] Documentation updates
- [ ] Code review preparation
- [ ] Final verification
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.
- 7d ago Changed · +26 lines · +24 tokens per session 72076e805917
- 1mo ago First seen · 70 lines · 20 tokens per session scan A 7f3e730d4b62
ccc-feature-start is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 1,043 once invoked, about $0.0002 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 commands, from other repositories
loop
Autonomous execution loop. Runs the TDD cycle repeatedly until all tasks in an epic are complete, with circuit breaker protection and PR workflow.
execute
Execute the next available tracked task with TDD, pre-commit validation, PR creation, AI code review, and issue tracker bridge sync.
symfony-tdd-pest
Start a TDD workflow using Pest PHP for Symfony with RED-GREEN-REFACTOR cycle.
debug
Systematic root-cause investigation, then fix with TDD — never proposes a fix before finding the cause; resumable diagnosis + regression test in .orc/ state. Workspace-aware. For a quick one-off look without session state, prefer the bundled /debug.
dev-tdd
Implements a feature by following the TDD (Test-Driven Development) cycle.
work-flow-feature
Complete workflow for developing a new feature, from exploration to merge.