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 Cody-W-Tucker/Cognitive-Assistant --skill decision-calibrationgit clone --depth 1 https://github.com/Cody-W-Tucker/Cognitive-AssistantWrote 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/cody-w-tucker/cognitive-assistant/decision-calibration)<a href="https://agentmods.dev/skills/cody-w-tucker/cognitive-assistant/decision-calibration"><img src="https://agentmods.dev/badge/skills/cody-w-tucker/cognitive-assistant/decision-calibration/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/cody-w-tucker/cognitive-assistant/decision-calibration"><img src="https://agentmods.dev/badge/skills/cody-w-tucker/cognitive-assistant/decision-calibration.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 | $0.00052 | $0.01996 |
| Opus 5 | $0.00026 | $0.00998 |
| Sonnet 5 | $0.00010 | $0.00399 |
| Haiku 4.5 | $0.00005 | $0.00200 |
Grade B, and why
decision-calibration scanned grade B with 1 finding 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 11d 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
Run options against: fear, guilt, nostalgia, external approval, loyalty-as-self-abandonment, fear of going alone. Name which inputs are active. Guilt appearing as a decision input gets named as guilt before it is weighed How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision Calibration
When To Use
Load this when the request involves a pending decision, a relational/partnership tension, a commitment being avoided, or a stretch of reflection that is producing depth but no movement. Signals:
- Keeps reframing instead of acting; asks for one more model/lens
- Narrates a conflict held privately; weighs loyalty against ending something
- "I already understand this" but no date, ask, terms, or ship
- Guilt, nostalgia, or empathy is doing decision work
- Partnership continue/restructure/exit without explicit terms on the table
- Stretch goal framed as needing more preparation before any contact with reality
- Revenue/exposure/ask delayed behind product or system polish
Do Not Use
- Factual lookups, coding, formatting, logistics, or any request with a clear deliverable already named
- Pure mode detection before a decision is even in view — use
mode-detectionfirst - Daily-review observational passes — do not diagnose character or avoidance there
- Explicit vision/paradigm exploration mid-pass — advance the object; do not force a premature commit (see mode-detection exception)
What This Protects
The core failure: a generic model treats reflective register as an invitation to mirror it — impressive depth, more frameworks, generic reassurance, or validation of guilt. To this user that reads as dead, condescending, or a new place to hide. Over-explaining what he already knows is condescension. Mirroring his reflective register at length adds no decision pressure.
He measures help by whether reflection became behavior. Knowing as a substitute for choosing is the named trap.
Calibration Sequence
Run in order. Stop when the decision pressure is real and the next move is named.
-
Name the decision object What exactly is being chosen, deferred, or half-held? One sentence. If multiple decisions are tangled, split them; calibrate one.
-
Framework trap check Is this exchange producing more analysis and zero commitment? Is the conversation becoming the new structure he hides inside? If yes: stop adding structure; push toward the act (outreach, selling, deciding, apologizing, setting expectations, shipping). Treat "can you give me a framework for this" as a possible avoidance signal, not only a request to fulfill — unless vision/paradigm exception applies.
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.
- 11d ago First seen · 135 lines · 52 tokens per session scan B 530a3e26cc03
decision-calibration is a skill published in the GitHub repository Cody-W-Tucker/Cognitive-Assistant (11 stars, last pushed 24d ago), licensed Apache-2.0. It adds 52 tokens to every session and 1,996 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
covey-seven-habits
Applies Stephen Covey's Seven Habits framework for personal and interpersonal effectiveness, progressing from dependence through independence to interdependence. Covers proactivity, mission clarity, prioritization, Win/Win thinking, empathic listening, synergy, and renewal. Use when conducting personal effectiveness…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…