decisive-action

decisive-action is a skill for Claude Code from athola/claude-night-market. It costs 30 tokens per session (1,285 once invoked), scanned A, original, MIT.

Guidance for deciding when a coding agent should ask a question and when it should proceed with the available instructions.

In plain words
What is it for?
It helps judge requests involving destructive operations, security, data migrations, breaking changes, or several materially different implementation choices.
Why use it?
It reduces delays from unnecessary questions while highlighting cases where ambiguity could cause costly or unsafe changes.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the conserve plugin — 15 skills, 6 commands, 5 agents shipped together

Good fit It helps judge requests involving destructive operations, security, data migrations, breaking changes, or several materially different implementation choices.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/athola/claude-night-market/decisive-action
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 athola/claude-night-market --skill decisive-action
Clone the repo
git clone --depth 1 https://github.com/athola/claude-night-market

Made for: Claude Code.

Or install conserve, the plugin that ships this one along with the rest of its 15 skills, 6 commands, 5 agents.

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 decisive-action

README.md
[![agentmods](https://agentmods.dev/badge/skills/athola/claude-night-market/decisive-action/github.svg)](https://agentmods.dev/skills/athola/claude-night-market/decisive-action)
Your own site
<a href="https://agentmods.dev/skills/athola/claude-night-market/decisive-action"><img src="https://agentmods.dev/badge/skills/athola/claude-night-market/decisive-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.

agentmods 80×15 button for decisive-action

Your own site · 80×15
<a href="https://agentmods.dev/skills/athola/claude-night-market/decisive-action"><img src="https://agentmods.dev/badge/skills/athola/claude-night-market/decisive-action.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,285 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: 2 findings, 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 55
    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.
  • medium Excessive Agency · line 68
    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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.01285
Opus 5 $0.00015 $0.00642
Sonnet 5 $0.00006 $0.00257
Haiku 4.5 $0.00003 $0.00128

Measured 8d ago against content hash 55d2d254d2aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

decisive-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 8d 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.

plugins/conserve/skills/decisive-action/SKILL.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Decisive Action

Guidance on when to ask clarifying questions versus proceeding autonomously.

When To Use

  • Reducing unnecessary clarifying questions
  • Taking autonomous action when intent is clear

When NOT To Use

  • High-stakes irreversible operations requiring explicit confirmation
  • Ambiguous requirements where clarification prevents wasted work

Core Principle

Ask questions only when ambiguity would materially impair correctness or capacity to fulfill the request precisely.

When to Ask (High Impact Ambiguity)

Always Ask For

Scenario Why Example
Destructive Operations Irreversible, high cost of error "Delete which files?"
Multiple Valid Approaches Materially different tradeoffs "Add index vs cache vs denormalize?"
Security-Critical Wrong choice = vulnerability "Which auth method?"
Data Migration Data loss risk "Preserve or transform?"
Breaking Changes Affects downstream users "Deprecate or remove?"

Ask Threshold Checklist

Before asking, verify:

  • >30% chance of wrong interpretation
  • Error cost > correction cost
  • No clear standard approach exists
  • User context doesn't clarify intent

When to Proceed Without Asking

Default to Action For

Scenario Why Assumption
Standard Approach Exists Industry convention Use conventional pattern
Easily Reversible Low cost of error Can undo via git/backup
Clear from Context Intent is obvious Proceed with stated goal
User Can Review PR/dry-run available Changes are inspectable

Proceed Threshold Checklist

Proceed without asking if:

  • Standard/obvious solution exists
  • Easily reversible (git, backup)
  • User can review before finalize
  • Context makes intent clear
  • Error cost < interruption cost

Decision Matrix

Reversibility Ambiguity Action
Reversible Low Proceed
Reversible High Proceed with preview
Irreversible Low Proceed with confirmation
Irreversible High Ask

Read the full file on GitHub · 198 lines

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. 8d ago First seen · 198 lines · 30 tokens per session scan A 55d2d254d2aa

Subscribe to this mod's changes

decisive-action is a skill published in the GitHub repository athola/claude-night-market (337 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 1,285 once invoked, about $0.0002 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 2026-09-03.