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 escapeboy/ai-prompts --skill decision-classifygit clone --depth 1 https://github.com/escapeboy/ai-promptsWrote 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/escapeboy/ai-prompts/decision-classify)<a href="https://agentmods.dev/skills/escapeboy/ai-prompts/decision-classify"><img src="https://agentmods.dev/badge/skills/escapeboy/ai-prompts/decision-classify/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/escapeboy/ai-prompts/decision-classify"><img src="https://agentmods.dev/badge/skills/escapeboy/ai-prompts/decision-classify.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 | $0.00020 | $0.01058 |
| Opus 5.5 | $0.00008 | $0.00423 |
| Sonnet 5.5 | $0.00004 | $0.00212 |
| Haiku 4.5 | $0.00002 | $0.00106 |
Grade A, and why
decision-classify 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/decision-classify - Decision Classification Framework
Classify intermediate decisions during skill or agent execution to determine which need user input and which can be auto-resolved.
When to Use (and When NOT to)
| Use this skill for | Use a simpler approach for |
|---|---|
| A mid-execution decision where it's unclear whether to ask the user | An obviously mechanical choice (one clearly correct answer) — just make it |
| Deciding whether to interrupt with a question or proceed and log the choice | A decision the user already explicitly specified — just follow it |
| Framing a case where the agent thinks the user's direction should change | Routine implementation choices with no real tradeoff — skip classification |
Usage
/decision-classify [context]
Run this when a skill or agent faces a decision during execution. It classifies the decision and recommends the appropriate handling.
The Three Types
1. Mechanical — Auto-decide silently
One clearly correct answer. Reasonable engineers would all choose the same.
Examples: Import ordering, file placement following conventions, variable naming per project style, dependency version resolution.
Test: Would two senior engineers independently make the same choice?
2. Taste — Auto-decide, surface later
Multiple valid approaches. One is slightly better for this context but the other is defensible.
Examples: Extract helper vs inline, choosing between equivalent libraries, component granularity, unit vs integration test for a case.
Surface as:
TASTE DECISION: [what was decided]
Chose: [option] because [reason]
Alternative: [other option] — would work if [condition]
Test: Could a senior engineer reasonably prefer the other option?
3. User Challenge — ALWAYS ask
The agent believes the user's stated direction should change.
Examples: User asked for REST but WebSocket fits better, requested feature contradicts architecture, scope will take 10x longer than expected, security concern.
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 · 129 lines · 20 tokens per session scan A f40a4d912fef
decision-classify is a skill published in the GitHub repository escapeboy/ai-prompts (91 stars, last pushed 9d ago), licensed MIT. It adds 20 tokens to every session and 1,058 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 2026-10-08.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…