skill-progressive-disclosure-design

skill-progressive-disclosure-design is a skill for Claude Code, Codex from OutlineDriven/odin-claude-plugin. It costs 68 tokens per session (2,290 once invoked), scanned A, original, Apache-2.0.

A design guide for deciding whether a long agent skill should stay in one file or be split into linked reference files.

In plain words
What is it for?
Use it when creating or refactoring skills, especially when a SKILL.md has grown beyond roughly 300–400 lines, to plan the file structure and checks.
Why use it?
It separates triggering problems from disclosure problems: how an agent recognizes a skill is different from how much of its instructions it reads at once.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the odin-agent plugin — 46 skills shipped together

Good fit Use it when creating or refactoring skills, especially when a SKILL.md has grown beyond roughly 300–400 lines, to plan the file structure and checks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/outlinedriven/odin-claude-plugin/skill-progressive-disclosure-design
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 OutlineDriven/odin-claude-plugin --skill skill-progressive-disclosure-design
Clone the repo
git clone --depth 1 https://github.com/OutlineDriven/odin-claude-plugin

Made for: Claude Code, Codex.

Or install odin-agent, the plugin that ships this one along with the rest of its 46 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 skill-progressive-disclosure-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/skill-progressive-disclosure-design/github.svg)](https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/skill-progressive-disclosure-design)
Your own site
<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/skill-progressive-disclosure-design"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/skill-progressive-disclosure-design/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 skill-progressive-disclosure-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/skill-progressive-disclosure-design"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/skill-progressive-disclosure-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,290 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00068 $0.02290
Opus 5 $0.00034 $0.01145
Sonnet 5 $0.00014 $0.00458
Haiku 4.5 $0.00007 $0.00229

Measured 6d ago against content hash 7c417245f72a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

skill-progressive-disclosure-design 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 6d 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.

plugins/odin-agent/skills/skill-progressive-disclosure-design/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill progressive disclosure design

Contract

Field Bound contract
Trigger the model is creating or refactoring a skill, faces a SKILL.md over 300-400 lines, or confuses triggering with disclosure
Authority reversible-local: write only named local skill files; rollback by restoring prior file contents
Side effect restructures the skill's files (split or monolith with reference pointers), limited to the target skill directory
Done justified split-or-monolith decision with pointer hygiene and an architecture-eval plan

Inputs

  • The existing skill directory (SKILL.md, any references/, scripts/). Required.
  • The skill's YAML description. Required for triggering diagnosis.
  • Empirical evidence (eval transcripts, token counts) if available. Optional; absence triggers the instrumentation recommendation path.

Procedure

  1. Diagnose triggering vs. disclosure. Separate these two problems before deciding whether to split.

    • Triggering is whether the model invokes the skill at all. Driven entirely by the YAML description. File splitting does not affect triggering. If the question is "my skill doesn't trigger reliably", do not split files. Fix the description.
    • Progressive disclosure is what loads after the skill activates. SKILL.md body always loads. references/* only loads when SKILL.md tells the model to read a specific file. scripts/* executes without loading into context. This is where context protection happens.
    • If the user asks about splitting because of triggering issues, surface the confusion first and redirect. Do not recommend structural changes until the triggering question is resolved. Done when: the problem is classified as triggering, disclosure, or both, and the user understands the distinction.
  2. Default: do not split. A monolithic SKILL.md beats a split one until proven otherwise. Split only when at least one holds:

    • SKILL.md exceeds ~400 lines and content has natural branches.
    • Empirical evidence (eval transcripts) shows the model wasting context on irrelevant sections.
    • Specific content is large and only needed in narrow conditions.
    • Record the rationale for the monolith-or-split decision before proceeding.
    • Monolith pros: single context load, no router prose, no wrong-load risk, one source of truth, easier human review.
    • Monolith cons: every invocation pays full token cost, does not scale past ~500 lines, no mechanism to gate rare content. Done when: the default is stated and the specific conditions that would override it are recorded.

Read the full file on GitHub · 117 lines

Files

What ships with it

1 file 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.

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. 6d ago First seen · 117 lines · 68 tokens per session scan A 7c417245f72a

Subscribe to this mod's changes

skill-progressive-disclosure-design is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed yesterday), licensed Apache-2.0. It adds 68 tokens to every session and 2,290 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 2026-09-04.

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