What is confirm-action?

A confirmation step that asks a user to approve or reject a significant action before it happens. It can present standard or custom response choices and passes the answer to the workflow.

Use it before isolating devices, disabling accounts, blocking addresses or domains, stopping processes, deleting files, escalating incidents, or closing high-severity alerts as false positives.

It adds a human check before actions that could disrupt systems, accounts, networks, files, or investigations.

confirm-action — Skill for Claude Code and Codex by dandye/ai-runbooks

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.

Any agent

npx skills add dandye/ai-runbooks --skill confirm-action

Clone the repo

git clone --depth 1 https://github.com/dandye/ai-runbooks

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dandye/ai-runbooks/confirm-action/github.svg)](https://agentmods.dev/skills/dandye/ai-runbooks/confirm-action)

Your own site

<a href="https://agentmods.dev/skills/dandye/ai-runbooks/confirm-action"><img src="https://agentmods.dev/badge/skills/dandye/ai-runbooks/confirm-action/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/dandye/ai-runbooks/confirm-action"><img src="https://agentmods.dev/badge/skills/dandye/ai-runbooks/confirm-action.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 505 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 53
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

How audits are shown

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 5.1	$0.00036	$0.00505
Opus 5.5	$0.00014	$0.00202
Sonnet 5.5	$0.00007	$0.00101
Haiku 4.5	$0.00004	$0.00051

Measured 2mo ago against content hash 3b21b693fb75, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

confirm-action 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 2mo 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/confirm-action/SKILL.md · 78 lines

What it actually says

Confirm Action Skill

Ask the user a confirmation question before proceeding with a significant action.

Inputs

QUESTION_TEXT - The specific question to ask (e.g., "Isolate endpoint WORKSTATION-01?", "Proceed with account disable for jsmith?")
(Optional) RESPONSE_OPTIONS - Predefined options for the user:
- Default: ["Yes", "No"]
- Custom examples: ["Disable Account", "Reset Password", "Monitor Only"]

Workflow

Step 1: Present Question

Display the question to the user with available options.

Step 2: Wait for Response

Collect the user's selection or custom input.

Step 3: Return Response

Provide the response back to the calling workflow for decision branching.

Outputs

Output	Description
`USER_RESPONSE`	The user's answer to the confirmation question

When to Use

Always confirm before:

Isolating/quarantining endpoints
Disabling user accounts
Blocking IPs/domains at firewall
Terminating processes
Deleting files
Escalating to incident response
Closing cases as false positive (for high-severity alerts)

May skip confirmation for:

Adding comments to cases
Running enrichment queries
Generating reports
Read-only operations

Example Confirmations

Containment:

Question: "Isolate endpoint WORKSTATION-01 from the network?"
Options: ["Yes - Isolate", "No - Continue Monitoring", "Escalate First"]

Account Action:

Question: "User jsmith shows signs of compromise. What action?"
Options: ["Disable Account", "Force Password Reset", "Monitor Only", "Escalate to IR"]

Case Closure:

Question: "Close case 1234 as False Positive?"
Options: ["Yes - Close FP", "No - Keep Open", "Escalate to Tier 2"]

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.

2mo ago First seen · 78 lines · 36 tokens per session scan A 3b21b693fb75

Subscribe to this mod's changes

confirm-action is a skill published in the GitHub repository dandye/ai-runbooks (132 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 36 tokens to every session and 505 once invoked, about $0.0001 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 2026-08-30.

Planning Security

confirm-action next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
confirm-actiondandye/ai-runbooks	Skill	132	2mo ago	Apache-2.0	A	36	Claude Code, Codex
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	yesterday	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	100k	yesterday	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	315k	5d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code