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 huntsyea/thinking-skills --skill decision-auditorgit clone --depth 1 https://github.com/huntsyea/thinking-skillsWrote 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/huntsyea/thinking-skills/decision-auditor)<a href="https://agentmods.dev/skills/huntsyea/thinking-skills/decision-auditor"><img src="https://agentmods.dev/badge/skills/huntsyea/thinking-skills/decision-auditor/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/huntsyea/thinking-skills/decision-auditor"><img src="https://agentmods.dev/badge/skills/huntsyea/thinking-skills/decision-auditor.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 | $0.00067 | $0.00649 |
| Opus 5 | $0.00034 | $0.00324 |
| Sonnet 5 | $0.00013 | $0.00130 |
| Haiku 4.5 | $0.00007 | $0.00065 |
Grade A, and why
decision-auditor 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 10d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision Auditor
Based on Thinking, Fast and Slow by Daniel Kahneman.
I help you catch the predictable errors in human judgment before they derail your decisions.
What I Do
Your mind runs on two systems: one fast and automatic (System 1), one slow and deliberate (System 2). Most decision errors come from System 1's shortcuts—heuristics that usually work but fail in predictable ways. I help you spot these failures and correct for them.
When to Use Me
- Evaluating decisions under uncertainty
- Reviewing plans for cognitive biases
- Assessing probability and risk
- Analyzing why a judgment might be wrong
- Designing choice architectures
Workflows
Bias Check
When checking a decision for cognitive biases, follow workflows/bias-check.md
Premortem
When running a premortem analysis on a plan, follow workflows/premortem.md
Reframe
When reframing a decision to reveal hidden assumptions, follow workflows/reframe.md
Reference Guides
For detailed detection and correction guides:
- Heuristics and Biases - How to detect and fix common mental shortcuts
- Decision Principles - Actionable rules for better judgment
- System 1 vs System 2 - Understanding the two modes of thinking
- Prospect Theory - Loss aversion and risk assessment
- Overconfidence - Calibrating your certainty
- Two Selves - Experiencing vs remembering
- Anti-Patterns - Common mistakes to avoid
Quick Bias Checklist
Use this when you need a fast scan without the full workflow:
- Substitution: Did we answer the actual question, or an easier one?
- WYSIATI: What information is missing that would be relevant?
- Base rates: What happens to similar cases? Are we treating ours as special?
- Anchoring: Where did our initial estimate come from? Would a different starting point change it?
- Availability: Are we overweighting vivid, recent, or personal examples?
- Affect: Are we conflating "I like this" with "this will succeed"?
- Overconfidence: Is our confidence level justified by the evidence?
- Planning fallacy: Are our estimates based on best-case scenarios?
What ships with it
10 files 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.
- references/anti-patterns.md 7.2 KB
- references/heuristics-biases.md 6.5 KB
- references/overconfidence.md 5.7 KB
- references/principles.md 6.5 KB
- references/prospect-theory.md 5.0 KB
- references/two-selves.md 6.1 KB
- references/two-systems.md 4.1 KB
- workflows/bias-check.md 4.0 KB
- workflows/premortem.md 4.4 KB
- workflows/reframe.md 6.5 KB
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.
- 10d ago First seen · 58 lines · 67 tokens per session scan A 05ca95eea015
decision-auditor is a skill published in the GitHub repository huntsyea/thinking-skills (4 stars, last pushed 7mo ago), licensed MIT. It adds 67 tokens to every session and 649 once invoked, about $0.0003 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
workers-best-practices
Cloudflare Workers best practices for production applications. Use when writing, reviewing, or configuring Workers.
find-journalists
Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.
story-origin-check
Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
annotating-task-lineage
Annotate Airflow tasks with data lineage using inlets and outlets. Use when the user wants to add lineage metadata to tasks, specify input/output datasets, or enable lineage tracking for operators without built-in OpenLineage extraction.
managing-astro-local-env
Manage local Airflow environment with Astro CLI (Docker and standalone modes). Use when the user wants to start, stop, or restart Airflow, view logs, query the Airflow API, troubleshoot, or fix environment issues. For project setup, see setting-up-astro-project.