mode-detection

mode-detection is a skill for Claude Code, Codex from Cody-W-Tucker/Cognitive-Assistant. It costs 66 tokens per session (2,445 once invoked), scanned A, original, Apache-2.0.

A guide for noticing when a request for more thinking, frameworks, or analysis is covering up a need to act or have a direct conversation. It helps identify the real mode of the situation.

In plain words
What is it for?
Use it when someone wants to keep exploring a relationship, boundary, partnership, strategy, or hard conversation without naming the next move.
Why use it?
It reduces abstract planning when the person already understands the problem but is delaying a constrained next step. It also flags when technical or faith-based reflection may be standing in for outward action.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions OpenCode.

Good fit Use it when someone wants to keep exploring a relationship, boundary, partnership, strategy, or hard conversation without naming the next move.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cody-w-tucker/cognitive-assistant/mode-detection
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 Cody-W-Tucker/Cognitive-Assistant --skill mode-detection
Clone the repo
git clone --depth 1 https://github.com/Cody-W-Tucker/Cognitive-Assistant

Made for: Claude Code, Codex.

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 mode-detection

README.md
[![agentmods](https://agentmods.dev/badge/skills/cody-w-tucker/cognitive-assistant/mode-detection/github.svg)](https://agentmods.dev/skills/cody-w-tucker/cognitive-assistant/mode-detection)
Your own site
<a href="https://agentmods.dev/skills/cody-w-tucker/cognitive-assistant/mode-detection"><img src="https://agentmods.dev/badge/skills/cody-w-tucker/cognitive-assistant/mode-detection/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 mode-detection

Your own site · 80×15
<a href="https://agentmods.dev/skills/cody-w-tucker/cognitive-assistant/mode-detection"><img src="https://agentmods.dev/badge/skills/cody-w-tucker/cognitive-assistant/mode-detection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,445 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.
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 $0.00066 $0.02445
Opus 5 $0.00033 $0.01222
Sonnet 5 $0.00013 $0.00489
Haiku 4.5 $0.00007 $0.00245

Measured 10d ago against content hash 7f8be7c4cf1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mode-detection 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.

workspaces/skills/existential/mode-detection/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mode Detection

When To Use

Load this when a request shows any of these shapes:

  • A call for more structure, frameworks, models, or analysis on a problem he can already articulate.
  • Wanting to "explore" or "think through" a relational situation, boundary, or hard conversation.
  • Framing a person (partner, spouse, mentor, collaborator) as something to manage, optimize, or strategize.
  • Guilt about responsiveness, availability, or not handling a relationship perfectly.
  • Reaching for certainty, more validation, or more options before committing to a constrained path.
  • A partnership continue-vs-end question presented as logistics.
  • Faith-coded reflection that risks turning into abstraction.
  • Something described as "off," misaligned, or unresolved without a named next move.
  • Post-cleanup emptiness: wanting chaos, intensity, or more internal architecture back when bandwidth is high.
  • Backend/system work that may be standing in for an outward ask, sale, ship, or confrontation.

Do Not Use

  • Pure technical, factual, formatting, or procedural tasks.
  • When he genuinely lacks the conceptual map (rare) and a framework is the actual missing piece.
  • When the request is concrete execution help already pointed at the right action.
  • Daily-review / close-out analysis: stay observational there; do not load this skill to diagnose avoidance or character. (See cognitive-assistant-system close-out rules.)

Core Read

This user is a systems-oriented builder who treats his own life as a knowledge problem to metabolize into coherence. His mind sees the architecture quickly; his bottleneck is execution under emotional and relational ambiguity — not insight deficit. He already produces frameworks and emotional insight in abundance and can use both to stall.

Treat understanding as already present. The scarce resources are execution, shipping, direct conversation, and contact with external reality. More depth is usually the wrong gift.

Signature trap: analysis, planning, and system-building as sophisticated avoidance of a concrete relational or shipping move he already senses is next. Protection, not laziness. Avoidance is localized — especially where he feels dependent (partners, mentors) — not global; he can be forceful elsewhere.

Read the full file on GitHub · 143 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. 10d ago First seen · 143 lines · 66 tokens per session scan A 7f8be7c4cf1f

Subscribe to this mod's changes

mode-detection is a skill published in the GitHub repository Cody-W-Tucker/Cognitive-Assistant (11 stars, last pushed 23d ago), licensed Apache-2.0. It adds 66 tokens to every session and 2,445 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 83 tokens

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…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens