cognitive-scaffolding

cognitive-scaffolding is a skill for Claude Code from itallstartedwithaidea/agent-skills. It costs 38 tokens per session (2,335 once invoked), scanned A, original, MIT.

A method for arranging information in an AI agent's context so important details receive more attention. It draws on ideas such as placing key information at the beginning or end and grouping related details into chunks.

In plain words
What is it for?
Organising prompts, code context, documentation, and campaign or project data so priorities, constraints, and other critical facts are easier for an agent to notice.
Why use it?
Long instructions and background material can cause important information to be overlooked. Deliberate ordering and grouping make the context easier for the agent to use when reasoning.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code; mentions Codex; mentions Gemini CLI.

Part of the claude-mythos-skills plugin — 10 skills shipped together , and of all-skills

Good fit Organising prompts, code context, documentation, and campaign or project data so priorities, constraints, and other critical facts are easier for an agent to notice.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/itallstartedwithaidea/agent-skills/cognitive-scaffolding
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 itallstartedwithaidea/agent-skills --skill cognitive-scaffolding
Clone the repo
git clone --depth 1 https://github.com/itallstartedwithaidea/agent-skills

Made for: Claude Code.

Or install claude-mythos-skills, the plugin that ships this one along with the rest of its 10 skills.

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 cognitive-scaffolding

README.md
[![agentmods](https://agentmods.dev/badge/skills/itallstartedwithaidea/agent-skills/cognitive-scaffolding/github.svg)](https://agentmods.dev/skills/itallstartedwithaidea/agent-skills/cognitive-scaffolding)
Your own site
<a href="https://agentmods.dev/skills/itallstartedwithaidea/agent-skills/cognitive-scaffolding"><img src="https://agentmods.dev/badge/skills/itallstartedwithaidea/agent-skills/cognitive-scaffolding/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 cognitive-scaffolding

Your own site · 80×15
<a href="https://agentmods.dev/skills/itallstartedwithaidea/agent-skills/cognitive-scaffolding"><img src="https://agentmods.dev/badge/skills/itallstartedwithaidea/agent-skills/cognitive-scaffolding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,335 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 $0.00038 $0.02335
Opus 5 $0.00019 $0.01167
Sonnet 5 $0.00008 $0.00467
Haiku 4.5 $0.00004 $0.00233

Measured 10d ago against content hash 4d9a6c96c33a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

cognitive-scaffolding 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.

skills/claude-mythos/cognitive-scaffolding/SKILL.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cognitive Scaffolding

Part of Agent Skills™ by googleadsagent.ai™

Description

Cognitive Scaffolding structures an agent's context window using principles from cognitive science — primacy effects, recency bias, chunking, and attention allocation. Language models, like human working memory, are not uniform processors. Information placed at the beginning and end of the context receives disproportionate attention (primacy and recency effects), while content in the middle can be effectively invisible. Cognitive Scaffolding exploits these properties to ensure the most critical information receives maximum model attention.

This skill was developed through extensive experimentation on the Buddy™ agent at googleadsagent.ai™, where analysis accuracy improved by measurable margins simply by restructuring how information was arranged in the context window. Campaign performance data placed at strategic positions within the prompt produced significantly better recommendations than the same data placed arbitrarily. The same principle applies to code context, documentation, and any other information an agent must reason over.

The cognitive scaffolding framework organizes context into four zones: the anchor zone (first 5% of context — highest attention, used for identity and immutable rules), the foreground zone (last 20% — high attention, used for the current task and recent context), the structured middle (60% — moderate attention, organized into clearly delimited chunks), and the background zone (15% — lowest attention, used for reference material and fallbacks). Each zone has specific content strategies that maximize the model's ability to utilize the information placed there.

Use When

  • Agent accuracy varies inconsistently despite using the same information
  • Long context windows degrade performance compared to shorter interactions
  • Critical instructions or constraints are occasionally ignored by the agent
  • You need to present large amounts of reference data without overwhelming the agent
  • Multi-document reasoning requires the agent to attend to specific sections
  • You are optimizing agent behavior for specific model architectures

Read the full file on GitHub · 220 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 · 220 lines · 38 tokens per session scan A 4d9a6c96c33a

Subscribe to this mod's changes

cognitive-scaffolding is a skill published in the GitHub repository itallstartedwithaidea/agent-skills (37 stars, last pushed 5mo ago), licensed MIT. It adds 38 tokens to every session and 2,335 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 2026-08-30.