progressive-disclosure SKILL.md skillA
progressive-disclosure from gptme/gptme-contrib is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add gptme/gptme-contrib/progressive-disclosure@v1.0.0Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- gptme/gptme-contrib
- Path
skills/progressive-disclosure/SKILL.md- Versions recorded
- 2
- Latest version
- v1.0.0, committed Feb 28, 2026
- First version recorded
- Dec 8, 2025
- Size
- 4,806 bytes
- Repository stars
- 15
- License
- MIT
Template and guide for restructuring large documentation files into token-efficient directory structures. Reduces context bloat by 40-60% while maintaining accessibility.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Progressive Disclosure for Documentation A pattern for restructuring large documentation files into slim indexes with on-demand subdirectories, reducing always-included context by 40-60%. ## Problem Large documentation files (500+ lines, 5k+ tokens) that are always included in context: - Waste context budget on rarely-needed content - Slow down response times - Crowd out more relevant information - Create cognitive overload ## Solution Split monolithic docs into: 1. **Slim index** (~20% of original) - Always included, provides overview + navigation 2. **Detail directories** - On-demand loading when specific topics needed ## Structure ```txt Before: TOOLS.md (~11k tokens always included) ├── Section 1 (rarely needed) ├── Section 2 (rarely needed) ├── ... (15+ sections) └── Section N (rarely needed) After: tools/ ├── README.md (~4k tokens always included) # Slim index ├── topic1/README.md # Detailed docs (~1k tokens each) ├── topic2/README.md # Loaded on-demand └── .../README.md # etc. ``` ## When to Use **Good candidates for progressive disclosure:** - Files > 500 lines or 5k tokens …
Read the whole file at its exact version.
How to install
mdr add gptme/gptme-contrib/progressive-disclosure@sha256:dc4e8afc543a5550The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_qlbnwvgjdr2ydsdv)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Dec 8, 2025 and Feb 28, 2026, about one every 82 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2026-02-28 | 9ab6d0e | 4,806 B | A | view · diff |
| git:20251208.6ac90f9 | 2025-12-08 | 6ac90f9 | 4,575 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4806 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
gptme/gptme-contrib · 15 stars · license MIT · pushed 2026-10-22 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_qlbnwvgjdr2ydsdv GET https://markdownregistry.com/api/v1/resolve?ref=gptme/gptme-contrib/progressive-disclosure GET https://markdownregistry.com/api/v1/blob/dc4e8afc543a555090dbe07ed15a38e9a9dc249ac0ac02bd4e4d9e53f9cc3250
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from gptme/gptme-contrib
Every file in gptme/gptme-contrib