atoi-project-work

atoi-project-work is a skill for Claude Code, Codex from creative-int/atoi-plugins. It costs 82 tokens per session (1,224 once invoked), scanned A, original, MIT.

Instructions for using Atoi Projects, Workspaces, and Tasks during coding work. A Workspace records the repository's source state, while a Task tracks a specific piece of work and its results, changes, checks, and proof.

In plain words
What is it for?
Use them to connect a repository to an Atoi project, bind its workspace, start or continue a task, and follow the task through review and proof.
Why use it?
They keep project identity and task outcomes in one controlled sequence, reducing the risk of working in the wrong repository or losing verification details.

Skill for Claude CodeCodex

Part of the atoi plugin — 3 skills, 1 MCP server shipped together

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 skills/creative-int/atoi-plugins/atoi-project-work
Any agent
npx skills add creative-int/atoi-plugins --skill atoi-project-work
Clone the repo
git clone --depth 1 https://github.com/creative-int/atoi-plugins

Made for: Claude Code, Codex.

Or install atoi, the plugin that ships this one along with the rest of its 3 skills, 1 MCP server.

Wrote 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.

agentmods badge for atoi-project-work

README.md
[![agentmods](https://agentmods.dev/badge/skills/creative-int/atoi-plugins/atoi-project-work.svg)](https://agentmods.dev/skills/creative-int/atoi-plugins/atoi-project-work)
Your own site
<a href="https://agentmods.dev/skills/creative-int/atoi-plugins/atoi-project-work"><img src="https://agentmods.dev/badge/skills/creative-int/atoi-plugins/atoi-project-work.svg" alt="Measured on agentmods" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,224 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 $0.00082 $0.01224
Opus 5 $0.00041 $0.00612
Sonnet 5 $0.00016 $0.00245
Haiku 4.5 $0.00008 $0.00122

Measured 4d ago against content hash 56015ca7b652, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

atoi-project-work 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 4d 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.

skills/atoi-project-work/SKILL.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Atoi Project Work

Use Atoi as the authority for project identity, Workspace source truth, and durable Task outcomes. Keep the sequence intact: Project → Workspace → Task → Result · Changes · Checks · Proof.

Preconditions

  1. Confirm the product CLI is connected:

    atoi account status --json
    atoi mcp status --probe --json
    
  2. If the account is disconnected, ask the user to run:

    atoi account login
    
  3. Never request, copy, print, or place an Atoi token in a plugin configuration. The local atoi mcp serve bridge owns credentials.

Choose the Surface

  • Prefer the atoi_projects, atoi_workspace, and atoi_tasks MCP tools when they are mounted in the current agent.
  • Use the public atoi CLI when shell access is available or when the task requires local source inspection or local application.
  • Use --json for machine-readable CLI calls.
  • Do not invent a second project, workspace, task, or proof schema.

Workflow

1. Resolve the Project

List Projects before creating one:

atoi project list --json

With MCP, call atoi_projects with action: "list".

Reuse a Project when its identity and repository match. Create only when no matching Project exists:

atoi project create \
  --name "My project" \
  --repo owner/repository \
  --branch main \
  --profile workspace-write \
  --json

With MCP, call atoi_projects with action: "create", name, repo_url, repo_branch, and default_task_profile.

Capture the returned Project ID. Treat it as the stable identifier for every following step.

2. Establish Workspace Source Truth

Inspect the Project's one stable Workspace:

atoi workspace show --project <project-id> --json

Bind it only when the intended repository, branch, or directory is absent or wrong:

atoi workspace bind \
  --project <project-id> \
  --repo owner/repository \
  --branch main \
  --directory /absolute/repository/path \
  --json

From the bound repository, report current local source truth:

Read the full file on GitHub · 192 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 192 lines · 82 tokens per session scan A 56015ca7b652

Subscribe to this mod's changes

atoi-project-work is a skill published in the GitHub repository creative-int/atoi-plugins (0 stars, last pushed 19d ago), licensed MIT. It adds 82 tokens to every session and 1,224 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

data-charts-tako

Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.

gooseworks-ai/goose-skills · 35 tokens

apollo-lead-finder

Two-phase Apollo.io prospecting: free People Search to discover ICP-matching leads, then selective enrichment to reveal emails/phones (credits per contact). Creates Apollo lists. Deduplicates against existing contacts by LinkedIn URL.

gooseworks-ai/goose-skills · 51 tokens

monorepo-management

Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.

wshobson/agents · 54 tokens

browse-and-evaluate

Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.

MoizIbnYousaf/Ai-Agent-Skills · 43 tokens

render-airdrop-carousel

Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…

gooseworks-ai/goose-skills · 207 tokens

render-3d-product-showcase

Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the brand-color canvas, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed at…

gooseworks-ai/goose-skills · 159 tokens