setup

A project initialization command for Coco. It creates the project’s .coco configuration directory, settings, Git hooks, and permissions; migrate mode updates missing settings without changing existing choices.

In plain words
What is it for?
Use it when adding Coco to a project, forcing configuration again with reset, or reconciling an existing setup with current defaults using migrate.
Why use it?
It gives Coco a project-specific setup and helps older configurations catch up with newer defaults. Existing settings can be compared without being silently replaced.

Command

Install

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.

agentmods
npx agentmods add commands/skullninja/coco-workflow/setup
Clone the repo
git clone --depth 1 https://github.com/skullninja/coco-workflow
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,249 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00046 $0.02249
Opus 5 $0.00023 $0.01125
Sonnet 5 $0.00009 $0.00450
Haiku 4.5 $0.00005 $0.00225

Measured yesterday against content hash a371d9d29840, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

setup 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 yesterday.

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.

commands/setup.md · 257 lines

How it starts

The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.

User Input

$ARGUMENTS

Migrate Mode

If $ARGUMENTS contains "migrate", run only this section and stop. Do not touch git hooks, gitignore, or permissions.

.coco/config.yaml is copied from config/coco.default.yaml once, at setup, and never consulted again. A project set up months ago keeps whatever the defaults were that day -- including defaults that have since been reversed because they were wrong. Migrate is how that gets reconciled without discarding deliberate choices.

1. Read both files.

cat .coco/config.yaml
cat "${CLAUDE_PLUGIN_ROOT}/config/coco.default.yaml"

2. Add keys the project is missing. For every key present in the default and absent from the project config, insert it with the default value and its comment, in the same section and position. This is safe and needs no confirmation -- an absent key already behaves as its default, so writing it changes nothing except making it visible and editable.

3. Report keys whose values differ. Do not change them. A differing value is usually a deliberate choice, and silently reverting it would be worse than the drift. Present them as a table:

Key Yours Current default Why the default changed
loop.pause_on_error true false Pausing on the first failure turns a flaky test into a full stop needing a human
loop.parallel.enabled false true Worktree isolation is proven; serial execution is the slow path

Only include a Why for keys whose default actually changed in a release. For a key that merely differs because the user set it, leave that cell --.

4. Offer to apply. Use AskUserQuestion listing each differing key that has a changed default, and apply only what the user selects. Never apply in bulk without asking, and never touch a key the user set to a non-default value that was not itself a changed default.

5. Report what was added, what was changed, and what was left alone.

Read the full file on GitHub · 257 lines

Changes

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.

  1. yesterday First seen · 257 lines · 0 tokens per session scan A a371d9d29840

Subscribe to this mod's changes

setup is a command published in the GitHub repository skullninja/coco-workflow (7 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 2,249 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 2026-08-31.