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 athola/claude-night-market --skill decisive-actiongit clone --depth 1 https://github.com/athola/claude-night-marketWrote 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/athola/claude-night-market/decisive-action)<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.
<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>- NVIDIA SkillSpector warn
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.
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 | $0.00030 | $0.01285 |
| Opus 5 | $0.00015 | $0.00642 |
| Sonnet 5 | $0.00006 | $0.00257 |
| Haiku 4.5 | $0.00003 | $0.00128 |
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.
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 |
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.
- 8d ago First seen · 198 lines · 30 tokens per session scan A 55d2d254d2aa
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.
Other skills, from other repositories
fly
Fly one thought to its destination across concurrent agents, on whatever the project and harness already have. Lands only when the user has accounted for every detail, never on an agent's say-so.
setup
Use when installing or refreshing sound taste rules in a project — an explicit "sound setup", starting work in a repo with no .claude/sound/, or a taste-not-defined nudge. Also use to re-run after a stack change (new framework, new package in a monorepo).
moo-authoring
Use when adding or changing a skill, hook, or runtime file in this repo — including deciding which unit a new capability should be.
land
Build a stepped deck an audience works through until one thing of it stays with them. Use when the user needs an audience to come away holding one thing.
toy
Build a world the human drives until how a thing behaves is intuitive. Use when the user needs to hold how something behaves and reading has not made it intuitive.
consult
Bring how named experts would think about the question. Use when the user wants expert thinking on a tradeoff, choice, or stuck problem — not a verdict.