A guide for operating Atoi, a tool that organizes coding work into Projects and tracked Tasks. It connects through the installed Atoi command-line tool and its authenticated bridge.

Use it to create or manage Atoi Projects, connect them to repositories or local folders, run and review Tasks, and inspect change sets or proof-backed drafts.

It keeps project state, repository bindings, task progress, checks, and proof in one governed workflow instead of leaving that context in ad hoc file edits.

atoi — Skill by creative-int

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

Any agent

npx skills add creative-int/atoi-plugins --skill atoi

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.

Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,271 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.

Model	Per session	Once invoked
Fable 5	$0.00076	$0.01271
Opus 5	$0.00038	$0.00635
Sonnet 5	$0.00015	$0.00254
Haiku 4.5	$0.00008	$0.00127

Measured 2d ago against content hash 1eedb972d695, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

atoi 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 2d 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/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Atoi

Operate Atoi through the installed product CLI's credential-safe MCP bridge. Atoi remains the authority for Projects, stable Workspaces, governed Tasks, change sets, checks, and proof.

Use When

The user asks to create, inspect, update, archive, or restore an Atoi Project.
A Project needs a stable repository, branch, or local-directory binding.
Work should run as a durable Atoi Task with explicit result and proof.
An existing Task needs status, continuation, cancellation, or change review.
The user wants a confirmed local apply or proof-backed draft pull request.

Do not use this skill for ordinary file edits that do not need Atoi state, or for direct access to Atoi's remote bearer endpoint.

Authenticate and Connect

The plugin never contains an Atoi credential. The product CLI owns the operator token and bridges local stdio to Atoi's authenticated HTTP MCP endpoint.

atoi account login
atoi account status --json
atoi mcp status --probe --json

Clients start the bridge with:

atoi mcp serve

atoi account login uses browser device authorization unless an operator explicitly supplies --token. The resulting operator token stays in the CLI's local credential backend. Never request, print, copy, or place that token in plugin configuration.

Core MCP Tools

atoi_projects manages governed Projects with list, get, create, update, archive, and restore.
atoi_workspace manages a Project's stable Workspace with show, bind, status, report, and changes.
atoi_tasks manages durable Tasks with list, get, start, cancel, continue, changes, apply, and draft-pr.

Prefer these tools when they are mounted. Use the public atoi CLI when shell access is needed for local Git inspection or local application.

Workflow

1. Resolve the Project

Call atoi_projects with action: "list" before creating anything. Reuse a matching Project. If none exists, call action: "create" with name, repo_url, repo_branch, and a default_task_profile of safe or workspace-write.

Read the full file on GitHub · 161 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.

references/mcp-contract.md 2.7 KB

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.

2d ago First seen · 161 lines · 76 tokens per session scan A 1eedb972d695

Subscribe to this mod's changes

atoi is a skill published in the GitHub repository creative-int/atoi-plugins (0 stars, last pushed 17d ago), licensed MIT. It adds 76 tokens to every session and 1,271 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.

Project management abbie agent-skills claude-code codex cursor developer-tools

etsy-category-listing

Etsy category page scraper: given an Etsy category URL (e.g. https://www.etsy.com/c/jewelry) and optional page number, returns paginated product listings with listingId, shopId, title, url, image, salePrice, originalPrice, currency, rating, reviewCount, shopName, isAd, freeShipping, badge from category and subcategory…

browser-act/skills · 209 tokens

human-approval

Request human approval before performing a SAFETY-CRITICAL, IRREVERSIBLE, or SCOPE-EXPANDING action — submit a structured context (action, scope, risk, consequence) plus options, then STOP the current turn. The platform redispatches the agent after the human decides. NEVER use for routine deliverables (writing docs /…

Prismer-AI/PrismerCloud · 168 tokens

firebase-analytics

Use when logging analytics events, setting user properties, configuring default event parameters, building funnels, or adding screen-view tracking.

evanca/flutter-ai-rules · 28 tokens

firebase-remote-config

Use when implementing feature flags, running A/B tests, setting parameter defaults, fetching/activating config, or enabling real-time config updates.

evanca/flutter-ai-rules · 33 tokens

git-master

MUST USE whenever a task needs a commit or git-history investigation. Covers atomic commits, staging, commit-message style, rebase, squash, fixup/autosquash, blame, bisect, reflog, git log -S/-G, and questions like who wrote this or when was this added. Do not use for ordinary code edits unless the user asks for git…

code-yeongyu/oh-my-openagent · 81 tokens

prismer-evolve-record

Record the outcome of applying an evolution strategy. Use after resolving an error where prismer-evolve-analyze provided a recommendation, to feed back success or failure to the network.

Prismer-AI/PrismerCloud · 41 tokens