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.
npx skills add creative-int/atoi-plugins --skill atoigit clone --depth 1 https://github.com/creative-int/atoi-pluginsWrote 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/skills/creative-int/atoi-plugins/atoi)<a href="https://agentmods.dev/skills/creative-int/atoi-plugins/atoi"><img src="https://agentmods.dev/badge/skills/creative-int/atoi-plugins/atoi/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/skills/creative-int/atoi-plugins/atoi"><img src="https://agentmods.dev/badge/skills/creative-int/atoi-plugins/atoi.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 | $0.00108 | $0.01880 |
| Opus 5.5 | $0.00043 | $0.00752 |
| Sonnet 5.5 | $0.00022 | $0.00376 |
| Haiku 4.5 | $0.00011 | $0.00188 |
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 1mo 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Atoi
Atoi is where the person's projects, conversations and governed work live. Through this plugin you act in Atoi with exactly the authority of their own account. Nothing you do is hidden from them: every action leaves a receipt they can read back in the app.
First, check you have hands
The atoi_* tools come from the local bridge atoi mcp serve, which the
person's installed Atoi CLI runs. If the tools are missing, or a call fails
with a login or transport error, check from a shell:
atoi account status --json
atoi mcp status --probe --json
- Disconnected, or
login-required: ask the person to runatoi account login, which opens browser device authorization. Do not suggestatoi login; that pairs a Computer and gives you no tools. - Never ask for, print, copy or store the operator token.
- Once connected,
atoi_doctorwith{"action": "status"}returns Atoi's readiness ledger.
The model
- A Workspace is a place the person belongs to. Their Personal
Workspace is used when you pass no
workspace_id. - Each Workspace has one Thread: the conversation with Atoi's agent.
- A Project holds durable intent and, for code work, one stable source binding: repository, branch, optional directory.
- A Task is governed work in a Project. Its outcome is four separate things: Result, Changes (one authoritative change set with an id and a fingerprint), Checks, and Proof (receipts).
The tools
| Tool | Actions |
|---|---|
atoi_projects |
list get create update archive restore |
atoi_workspace |
create update list show bind status report changes |
atoi_tasks |
list get start cancel continue changes apply draft-pr |
atoi_threads |
list get resolve send reply steer attach retry stop react approve deny launch pin unpin timings |
atoi_search |
search by query |
atoi_inbox |
list keep edit dismiss approve deny snooze |
atoi_ideas |
list refresh answer dismiss |
atoi_usage |
get |
atoi_plan |
list archive restore |
atoi_automations |
list get create update toggle trigger remove |
atoi_channels |
list get authorize revoke test |
atoi_skills |
list get enable disable remove |
atoi_plugins |
list get install enable disable remove |
atoi_settings |
get set unset authorize disconnect |
atoi_doctor |
status |
What ships with it
2 files 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.
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.
- 1mo ago Changed · -10 lines · +32 tokens per session b9d288bf837a
- 2mo ago First seen · 161 lines · 76 tokens per session scan A 1eedb972d695
atoi is a skill published in the GitHub repository creative-int/atoi-plugins (0 stars, last pushed 12d ago), licensed MIT. It adds 108 tokens to every session and 1,880 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
bazel-build-optimization
Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.
track-management
Use this skill when creating, managing, or working with Conductor tracks - the logical work units for features, bugs, and refactors. Applies to spec.md, plan.md, and track lifecycle operations.
feedback-page-generator
Deprecated compatibility entry for Feedback Page construction. This page is now maintained in Pagina; install and use page-builder to build a new Feedback Page.
status-page-generator
Deprecated compatibility entry for Status Page construction. This page is now maintained in Pagina; install and use page-builder to build a new Status Page.
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.