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-fork)<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-fork"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-fork/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-fork"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-fork.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 | $0.00046 | $0.01466 |
| Opus 5.5 | $0.00018 | $0.00586 |
| Sonnet 5.5 | $0.00009 | $0.00293 |
| Haiku 4.5 | $0.00005 | $0.00147 |
Grade A, and why
ccc-fork 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ccc-fork — explore approaches in parallel
CC Commander · /ccc-fork · isolated forks per approach, a measured comparison, and one clean merge.
Each fork is a branch explore/<id> checked out in its own worktree at ../<repo>-<id>, created from the current commit. The main checkout is never modified until you merge.
Arguments
$ARGUMENTS:
"<description>"or empty — create a fork (empty: ask for a short description in plain text)list— show active forkscompare— measured comparison of active forksmerge <id>— merge a fork into the branch you started fromdiscard <id>— remove a fork's worktree and branch
What happens
Create
-
Run
git status --porcelain. If the tree is dirty, ask whether to commit first or fork fromHEADwithout the uncommitted changes; forks never carry uncommitted work. -
Count active forks with
git branch --list 'explore/*'. At five, stop and ask the user to merge or discard one first. -
Set
<id>tofork-plus six random hex characters,<base>togit rev-parse --abbrev-ref HEAD, and<repo>to the basename ofgit rev-parse --show-toplevel. -
Create and label the fork:
git worktree add "../<repo>-<id>" -b "explore/<id>" git config "branch.explore/<id>.description" "<description>" git config "branch.explore/<id>.forkbase" "<base>" -
Verify with
git -C "../<repo>-<id>" rev-parse --abbrev-ref HEAD(printsexplore/<id>), then report the fork id, description, base commit (git rev-parse --short HEAD), branch and worktree path. -
Ask how to work the fork with AskUserQuestion (plain-text question where unavailable):
- 🟢 Work it here — the assistant edits and runs commands only inside
../<repo>-<id>until you say to return. - Parallel agent — spawn one Agent per approach with
isolation: worktree; each implements, runs the tests, and reports back. The user's selected model is preserved unless they choose another. - Separate session — run
claude --continue --fork-sessionin a second terminal to copy this conversation into a new session, thencd ../<repo>-<id>there. This forks the conversation only; the worktree isolates the files.
- 🟢 Work it here — the assistant edits and runs commands only inside
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 · -83 lines · +30 tokens per session 9fb689c5b084
- 1mo ago First seen · 184 lines · 16 tokens per session scan A a3f15035bed1
ccc-fork is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 1,466 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
justone-publish
Publish a completed JustOne build — create a public GitHub repo, push, and register on the gallery.
auto-claude
Invoke Auto-Claude autonomous coding framework for complex feature implementation.
dashboard
Compact visual progress dashboard with progress bar, task table, dependency graph, and active/blocked/next status.
doc-changelog
Generation and maintenance of the project changelog.
commit
Split the changes into atomic commits, preflight and push them. Pass --skip-preflight or --no-push to skip a step.
ops-gitflow
Manage the GitFlow branching model: init, feature, release and hotfix branches.