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 atoi-proof-reviewgit 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-proof-review)<a href="https://agentmods.dev/skills/creative-int/atoi-plugins/atoi-proof-review"><img src="https://agentmods.dev/badge/skills/creative-int/atoi-plugins/atoi-proof-review.svg" alt="Measured on agentmods" 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 | $0.00080 | $0.01114 |
| Opus 5 | $0.00040 | $0.00557 |
| Sonnet 5 | $0.00016 | $0.00223 |
| Haiku 4.5 | $0.00008 | $0.00111 |
Grade A, and why
atoi-proof-review 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 7d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Atoi Proof Review
Review the authoritative Task change set before any durable action. Keep inspection separate from confirmation, and preserve Atoi's idempotency and proof receipts.
Preconditions
You need a Task ID and a connected Atoi operator identity:
atoi account status --json
atoi mcp status --probe --json
If the Task has not reached a review or terminal boundary, return to
atoi-project-work.
Workflow
1. Inspect the Task
atoi task get <task-id> --json
atoi task changes <task-id> --json
With MCP, call atoi_tasks with action: "get" and then
action: "changes".
Record:
- Task status
- Result
- change-set ID
- change-set status
- fingerprint
- files and operations
- blockers
- checks
- proof receipt
Stop if the change set is absent, unverified, stale, or blocked. Do not repair or reinterpret it client-side.
2. Compare Workspace Truth
Before a local apply, run from the intended repository:
atoi workspace status --project <project-id> --json
Verify the local repository and branch match the Workspace binding. Note any dirty files and the current revision. Do not overwrite unrelated work.
For a draft pull request, confirm the Workspace has a repository binding and that the requested head branch is appropriate.
3. Present the Decision
Summarize the exact change set before asking for confirmation:
Task: <id>
Change set: <id>
Fingerprint: <fingerprint>
Files: <count and paths>
Checks: <pass/fail/pending>
Proof: <receipt>
Available actions: apply locally | publish draft PR | leave unchanged
The user's choice is an action boundary. Never infer confirmation from an earlier request to inspect or review.
4A. Apply Locally
Use the public CLI for the actual local write:
atoi task apply <task-id> \
--confirm \
--expected-change-set-id <change-set-id> \
--expected-change-set-fingerprint <fingerprint> \
--directory /absolute/repository/path \
--json
The expected ID and fingerprint bind confirmation to the inspected artifact.
The default idempotency key is derived from the fingerprint. Supply an
explicit --idempotency-key only when the caller has a stable key to reuse.
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.
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.
- 7d ago First seen · 175 lines · 80 tokens per session scan A d8bc83ec87e4
atoi-proof-review is a skill published in the GitHub repository creative-int/atoi-plugins (0 stars, last pushed 22d ago), licensed MIT. It adds 80 tokens to every session and 1,114 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.
Other skills, from other repositories
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
branch-pr
Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
chained-pr
Trigger: PRs over 400 lines, stacked PRs, review slices. Split oversized changes into chained PRs that protect review focus.
github-pr-creation
Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…
anchor-vet
Evidence-gated diff review for PRs, branches, commit ranges, staged code changes, and merge readiness checks. Use when an AI reviewer must review a concrete git-anchored diff, judge whether code is safe to merge, inspect a PR URL or branch, cross-examine PR or commit claims, account blast radius, or render…