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-parallel)<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-parallel"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-parallel/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-parallel"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-parallel.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 | $0.00036 | $0.01317 |
| Opus 5.5 | $0.00014 | $0.00527 |
| Sonnet 5.5 | $0.00007 | $0.00263 |
| Haiku 4.5 | $0.00004 | $0.00132 |
Grade A, and why
ccc-parallel 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 6d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ccc-parallel — parallel agents in git worktrees
CC Commander · /ccc-parallel · launches independent agents on separate branches and merges their work when they finish.
Usage
/ccc-parallel # interactive setup
/ccc-parallel 3 "<task prompt>" # three agents on the same task
$ARGUMENTS: optional agent count and task prompt.
Each agent gets a git worktree: a separate working directory that shares the repository history but has its own branch and file state. Each agent can read and write its own files, cannot see the others' uncommitted changes, and runs its own tests.
Main session (coordinator)
├── worktree 1 → feat/add-auth
├── worktree 2 → feat/add-dashboard
└── worktree 3 → feat/add-api-tests
What happens
-
Confirm the starting point:
git rev-parse --show-toplevel git status --short git branch --show-currentIf the tree is dirty, say so; worktrees branch from the committed HEAD, so uncommitted changes are not visible to the agents.
-
Collect the plan. If
$ARGUMENTSlacks a count or tasks, ask with AskUserQuestion:- 🟢 2 agents — easiest to merge and review.
- 3 agents — more throughput, more merge work.
- 4 or 5 agents — only for clearly independent tasks.
Then ask for one task and one branch name per agent. Use descriptive branch names so
git worktree listtells agents apart. -
Check independence: list the files or directories each task will touch. If two tasks touch the same files, tell the user and suggest running them in sequence instead.
-
Launch. Pick the mechanism with AskUserQuestion:
- 🟢 In-session subagents — parallel Agent tool calls with
isolation: worktree; results return to this session. - Separate terminals — the user runs one
claude -w <branch>per agent (add--tmuxfor a tmux session per worktree). - Workflow tool — one run with
parallel()where the Workflow tool is available.
Separate-terminal form:
- 🟢 In-session subagents — parallel Agent tool calls with
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.
- 6d ago Changed · -71 lines · +22 tokens per session 3eeb2f1c7ebf
- 1mo ago First seen · 229 lines · 14 tokens per session scan A 840b91198bb2
ccc-parallel is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 1,317 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 2026-09-04.
Other commands, from other repositories
undo-commit
Soft-undo the last commit. Restores its changes as staged, leaves working tree intact. Refuses if HEAD is already pushed to a tracked remote.
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.
commit
Stage, commit, and optionally ship further. Pass an escalation token (push, pr, merge, squash, squash merge) to skip the prompt. With no token, commits then asks how far to ship. Delegates message format to the atomic-git-discipline skill.
commit
Split the changes into atomic commits, preflight and push them. Pass --skip-preflight or --no-push to skip a step.
autocommit
Toggle auto git commits on/off for this project. Run without args to see status, or with "on"/"off" to set.
commit-message
Generate a conventional commit message from staged changes.