New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Context Architecture

by hashgraph-online in hashgraph-online/awesome-codex-plugins

Progressive disclosure architecture for organizing project context as a DAG (directed acyclic graph).

Apache-2.0Auto-check passedAgent Workflows

Install Context Architecture

skills CLI
$ npx skills add hashgraph-online/awesome-codex-plugins --skill context-architecture -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install hashgraph-online/awesome-codex-plugins context-architecture --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/JuliusBrussee/blueprint/skills/context-architecture .claude/skills/context-architecture && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
context-architecture
GitHub stars
1.2k
Token cost
~2.9k tokens
SKILL.md length
818 words
Files
1
Skills in repo
686
Repo updated
First seen
Licence
Apache-2.0

At a glance

Progressive disclosure architecture for organizing project context as a DAG (directed acyclic graph).

  • Works in 3 steps: Look in context/plans/ → If not found, fall back to context/sites/ → If found in sites/, use it — no…
  • Phrases: context architecture
  • SKILL.md covers Core Principle, The 4-Tier Information Flow, Directory Layout and CLAUDE.md Hierarchy, plus 8 more sections
  • Calls git

What it does

Context Architecture is an agent skill from hashgraph-online/awesome-codex-plugins. Progressive disclosure architecture for organizing project context as a DAG (directed acyclic graph). Agents enter at the root and traverse only the subgraph relevant to their task. Covers the 4-tier information flow (refs → kits → plans → impl), CLAUDE.md hierarchy across context/ and source tree, index files as DAG hub nodes, nesting rules, and backward compatibility. Trigger phrases: "context architecture", "progressive disclosure", "organize context for agents", "context directory structure", "how to…

Its SKILL.md is about 2.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Agent instruction files. The repository describes itself as: A curated list of awesome OpenAI Codex / ChatGPT plugins, skills, and resources. The 1 Codex Marketplace. See live plugins at: https://hol.org/plugins/best-codex-plugins. The licence is Apache-2.0.

When your agent uses it

  • Phrases: context architecture
  • Progressive disclosure
  • Organize context for agents
  • Context directory structure

Example prompts

  • “context architecture”
  • “progressive disclosure”
  • “organize context for agents”
  • “/context-architecture”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Look in context/plans/
  2. If not found, fall back to context/sites/
  3. If found in sites/, use it — no auto-migration, no breakage

What it can do on your machine

Read from SKILL.md and the folder at commit 78497e5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Context Architecture loads about 2.9k tokens when it runs. Until then it costs about 144 tokens; SKILL.md has 818 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~144
When it runs · the whole SKILL.md, loaded when a task matches
~2.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from hashgraph-online/awesome-codex-plugins at commit 78497e5, republished under its Apache-2.0 licence (© hashgraph-online). 818 words, ~2,930 tokens.

Download SKILL.mdSave it as .claude/skills/context-architecture/SKILL.md (or your agent's skills folder).
name
context-architecture
description
Progressive disclosure architecture for organizing project context as a DAG (directed acyclic graph). Agents enter at the root and traverse only the subgraph relevant to their task. Covers the 4-tier information flow (refs → kits → plans → impl), CLAUDE.md hierarchy across context/ and source tree, index files as DAG hub nodes, nesting rules, and backward compatibility. Trigger phrases: "context architecture", "progressive disclosure", "organize context for agents", "context directory structure", "how to structure docs for AI", "context hierarchy"

Context Architecture: DAG-Based Progressive Disclosure

Core Principle

Agents should only read what they need. Documents are organized as a directed acyclic graph (DAG) where index files act as hub nodes. An agent reads the index, identifies relevant edges, and follows only those to leaf documents. No agent ever loads the full tree.

The 4-Tier Information Flow

refs/ (what IS)  -->  kits/ (what MUST BE)  -->  plans/ (HOW)  -->  impl/ (what WAS DONE)
     Tier 1                  Tier 2                     Tier 3              Tier 4

Each tier consumes the previous tier's output. Cross-references between tiers create the DAG edges that agents traverse.

Directory Layout

context/
├── CLAUDE.md                              # Root entry node: describes all tiers + design layer
├── refs/                                  # Tier 1: Source material (read-only input)
│   ├── CLAUDE.md                          # "Source of truth. Organized by source. Read-only."
│   └── {source}/                          # Subdirs per source (e.g., prd/, api-spec/)
│       └── ...
├── kits/                            # Tier 2: WHAT to build
│   ├── CLAUDE.md                          # "Start at cavekit-overview.md. R-numbered reqs."
│   ├── cavekit-overview.md              # Index node (DAG hub)
│   ├── cavekit-{domain}.md              # Leaf — simple domain (single file)
│   └── {domain}/                          # Complex domain gets a subdirectory
│       ├── cavekit-{domain}.md          # Domain index (becomes hub node)
│       └── cavekit-{domain}-{sub}.md    # Sub-domain leaves
├── designs/                               # Cross-cutting: visual design system
│   ├── CLAUDE.md                          # "DESIGN.md at project root is canonical."
│   └── design-changelog.md               # Append-only change log
├── plans/                                 # Tier 3: HOW to build (task graphs)
│   ├── CLAUDE.md                          # "Start at plan-overview.md. Task dependency tiers."
│   ├── plan-overview.md                   # Index node
│   ├── build-site.md                      # Primary build site
│   ├── build-site-{feature}.md            # Feature-specific build sites
│   └── {domain}/                          # Complex plans get subdirectories
│       └── plan-{domain}-{area}.md
├── impl/                                  # Tier 4: What WAS DONE
│   ├── CLAUDE.md                          # "Start at impl-overview.md. Update after every session."
│   ├── impl-overview.md                   # Index node
│   ├── impl-{domain}.md                   # Per-domain tracking
│   ├── impl-review-findings.md            # Codex review findings ledger
│   ├── dead-ends.md                       # Failed approaches (shared across domains)
│   └── archive/                           # Compacted/archived tracking

Note: designs/ is a cross-cutting constraint layer, not a fifth tier. DESIGN.md (at project root) is read by agents at every Hunt phase — Draft reads it to constrain visual decisions, Architect references tokens in task descriptions, Build uses it for implementation, Inspect validates against it. It parallels how CLAUDE.md files provide conventions, but for visual design.

Backward Compatibility: sites/ → plans/

Build sites previously lived in context/sites/. All Cavekit commands check both locations:

  1. Look in context/plans/
  2. If not found, fall back to context/sites/
  3. If found in sites/, use it — no auto-migration, no breakage

/ck:init offers optional migration. Declining is permanent — the system works with either layout.

CLAUDE.md Hierarchy

Scope: Full Repository

CLAUDE.md files extend beyond context/ into the source code tree. They form the connective tissue between code and the context DAG.

project/
├── CLAUDE.md                          # Project root: build/test commands,
│                                      #   "context/ has the full hierarchy"
├── context/
│   ├── CLAUDE.md                      # Root context node: 4 tiers described
│   ├── refs/CLAUDE.md                 # Tier 1 conventions
│   ├── kits/CLAUDE.md           # Tier 2 conventions
│   ├── plans/CLAUDE.md                # Tier 3 conventions
│   └── impl/CLAUDE.md                 # Tier 4 conventions
│
├── src/
│   ├── CLAUDE.md                      # Source code conventions
│   ├── auth/
│   │   ├── CLAUDE.md                  # "implements cavekit-auth.md R1-R3"
│   │   └── ...
│   └── parser/
│       ├── CLAUDE.md                  # "implements cavekit-grammar.md R1-R4,
│       │                              #   see plans/build-site.md T-012 through T-018"
│       └── ...
│
├── tests/
│   ├── CLAUDE.md                      # Test conventions, how to run
│   └── ...
└── scripts/
    ├── CLAUDE.md                      # Utility script conventions
    └── ...
Loading Behavior

When an agent works in src/auth/, it loads hierarchically:

  1. project/CLAUDE.md — project-level conventions
  2. project/src/CLAUDE.md — source code conventions
  3. project/src/auth/CLAUDE.md — "implements cavekit-auth.md R1-R3"

The third file bridges to the context DAG. The agent knows which cavekit to load without loading the entire context/kits/ directory.

CLAUDE.md Design Principles
  • Minimal — 3-10 lines for source-tree files. Never duplicate cavekit content.
  • Connective — each one names the cavekit requirements and plan tasks it relates to.
  • Contextual — includes module-specific conventions (error handling patterns, test fixture locations).
  • Honest — /ck:make only writes mappings it is certain about (tasks it completed, files it created).

Progressive Disclosure: The DAG Traversal

How Agents Navigate
  1. Enter at root — read context/CLAUDE.md to understand the 4 tiers
  2. Select tier — based on current task, navigate to the relevant tier's CLAUDE.md
  3. Read index — the tier's overview file is the DAG hub, listing all domains with one-line summaries
  4. Follow edges — read only the domain files relevant to the current task
  5. Cross-reference — if a domain references another, follow that edge only if needed
  6. Nest deeper — if a domain has subdirectories, its root file is the sub-index; spider from there
Index File Format

Every overview file follows the same format:

markdown
# Cavekit Overview

| Domain | File | Summary | Status |
|--------|------|---------|--------|
| Authentication | cavekit-auth.md | Registration, login, sessions, OAuth | DRAFT |
| Data Models | cavekit-data-models.md | Core entities, relationships, validation | DRAFT |
| Type System | cavekit-type-system.md | Effects lattice, tagged values (see type-system/) | DRAFT |

An agent reads this table, identifies "I need Authentication," and loads only cavekit-auth.md.

Cross-Reference Edges
markdown
**Dependencies:** cavekit-auth.md R2 (session tokens required for API auth)
**See also:** cavekit-api.md R4 (rate limiting uses auth identity)

Agents follow these only when the cross-referenced content is needed for the current task.

Nesting Rule

A domain stays flat (single file) by default. When a file covers multiple independent concerns that could be understood separately, it becomes an index file pointing to a subdirectory.

Trigger: Cohesion, not line count. If a file has sections that an agent working on one section would never need to read the others, decompose it.

Example: cavekit-type-system.md covers effects lattice, tagged values, and inference rules:

kits/
├── cavekit-type-system.md                        # Now an index
└── type-system/
    ├── cavekit-type-system-effects.md
    ├── cavekit-type-system-tagged.md
    └── cavekit-type-system-inference.md

The original file stays in place as the index — no reference breakage.

Show full SKILL.md (302 more words)Show less

Backpropagation via CLAUDE.md

When a bug is found, source-tree CLAUDE.md files provide the reverse traversal:

Bug in src/auth/login.ts
    |
    v
src/auth/CLAUDE.md says "implements cavekit-auth.md R2"
    |
    v
cavekit-auth.md R2 — check acceptance criteria
    |
    |-- Criteria missing?  --> update cavekit (spec gap)
    |-- Criteria wrong?    --> fix cavekit (spec bug)
    |-- Criteria present but code violates? --> fix code (impl bug)
    |
    v
If cavekit changed --> propagate to plans/ --> flag affected tasks
Forward Propagation

When a cavekit changes via /ck:revise:

  1. Scan all src/*/CLAUDE.md files for references to the changed requirement
  2. Flag those modules as potentially affected
  3. New requirements with no source-tree CLAUDE.md references are unimplemented

Bootstrapping

Run /ck:init to create the full hierarchy. It:

  1. Scans existing project structure
  2. Creates context directories (refs/, kits/, plans/, impl/)
  3. Creates CLAUDE.md files using standard templates
  4. Creates empty index files (cavekit-overview.md, plan-overview.md, impl-overview.md)
  5. Offers migration if legacy context/sites/ exists

Properties: idempotent, non-destructive, no questions asked.

Build-Time Updates

After /ck:make completes, source-tree CLAUDE.md files are generated/updated:

  • New source directories get a CLAUDE.md with cavekit/plan references
  • Existing CLAUDE.md files get new references appended (never removed)
  • impl-overview.md and plan-overview.md are updated with current status

Multi-Repo Strategy

For shared kits across implementations, use git submodules:

Tier 1-2 (shared): shared-context/ (submodule)
    └── refs/ + kits/

Tier 3-4 (per-repo): context/
    └── plans/ + impl/

Each framework repo includes the shared context as a submodule. Updates propagate via git submodule update.

Integration with Other Skills

SkillIntegration
ck:cavekit-writingKits go in context/kits/ following naming conventions
ck:design-systemDESIGN.md lives at project root; context/designs/ has CLAUDE.md and changelog
ck:impl-trackingTracking lives in context/impl/, compacted when exceeding ~500 lines
ck:validation-firstValidation results recorded in impl tracking within the hierarchy
ck:revision/ck:revise traverses CLAUDE.md edges in reverse to trace bugs to specs
ck:methodologyContext structure established during Draft phase, maintained throughout the Hunt

Anti-Patterns

Anti-PatternWhy It's WrongFix
Flat file dumpNo progressive disclosure, agents load everythingUse standard directory structure with indexes
Missing CLAUDE.md filesNo convention guidance, no DAG edgesRun /ck:init or add manually
Monolithic documentsDefeats progressive disclosureDecompose into domains with overview indexes
Stale archives in active dirsWastes context windowMove to impl/archive/
Duplicating cavekit content in CLAUDE.mdContent drifts, double maintenanceCLAUDE.md files only contain references

© hashgraph-online, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/JuliusBrussee/blueprint/skills/context-architecture of hashgraph-online/awesome-codex-plugins.

Open the folder on GitHubat commit 78497e5

Compare with similar skills

Context Architecture next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Context Architecture compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Context Architecture this skillhashgraph-online/awesome-codex-plugins1.2k—~2.9kAutomated safety check: PassApache-2.0
Using Agent Skillsaddyosmani/agent-skills103k4 repos~2.4kAutomated safety check: PassMIT
Claude ReflectBayramAnnakov/claude-reflect1.7k2 repos~627Automated safety check: PassMIT
Writing For Agentsbestofjs/bestofjs3.1k19 repos~2.7kAutomated safety check: PassMIT
Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills21k—~1.9kAutomated safety check: PassMIT
Task Observerrebelytics/one-skill-to-rule-them-all3.2k1 repos~12kAutomated safety check: PassCC-BY-4.0

Similar skills

  • Using Agent Skills

    addyosmani/agent-skills

    Meta-skill for choosing which workflow skill fits the task at hand, plus always-on habits: surface assumptions, stop on confusion, push back, keep it simple and stay in scope.

    103k GitHub starsUsed in 4 repos~2.4k tokens
    Agent WorkflowsAuto-check passed

  • Claude Reflect

    BayramAnnakov/claude-reflect

    Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md.

    1.7k GitHub starsUsed in 2 repos~627 tokens
    Agent WorkflowsAuto-check passed

  • Writing For Agents

    bestofjs/bestofjs

    Writing documents for agents. An agent skill from bestofjs/bestofjs.

    3.1k GitHub starsUsed in 19 repos~2.7k tokens
    Agent WorkflowsAuto-check passed

  • Neat-Freak Knowledge Closeout

    KKKKhazix/khazix-skills

    Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.

    21k GitHub stars~1.9k tokensUpdated 7 days ago
    Agent WorkflowsAuto-check passed

  • Task Observer

    rebelytics/one-skill-to-rule-them-all

    Monitors task execution for skill improvement opportunities.

    3.2k GitHub starsUsed in 1 repo~12k tokens
    Agent WorkflowsAuto-check passed

  • SkillOpt Sleep Cycle

    microsoft/SkillOpt

    Official

    Runs an on-demand or nightly sleep cycle that reviews past Claude Code sessions and proposes validated updates to CLAUDE.md and skills.

    18k GitHub stars~2.3k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed

More from hashgraph-online/awesome-codex-plugins

All 686 skills in this repo

  • Anime Reaction Gif

    hashgraph-online/awesome-codex-plugins

    Create original anime-style reaction stickers as looping GIFs and MP4 previews, using generated character pose sheets and timed key poses.

    1.2k GitHub stars~922 tokensUpdated today
    Auto-check passed

  • Calibredb

    hashgraph-online/awesome-codex-plugins

    Manage and query Calibre libraries with the calibredb CLI (local paths or Calibre Content server URLs).

    1.2k GitHub stars~1k tokensUpdated today
    Auto-check passed

  • Rust API Test Harness

    hashgraph-online/awesome-codex-plugins

    A skill your agent uses when adding, changing, testing, or debugging Rust HTTP APIs and services, especially when Codex needs black-box integration tests, random-port app startup, real database test…

    1.2k GitHub stars~1.7k tokensUpdated today
    Auto-check passed

  • Art

    hashgraph-online/awesome-codex-plugins

    Make a studio's game look like something at build time — a cover from a real frame of the game (free), painted covers, backdrops, textures and character plates from image models through the…

    1.2k GitHub stars~2.4k tokensUpdated today
    Auto-check passed

  • Game Balance Economy

    hashgraph-online/awesome-codex-plugins

    Balance game difficulty, resources, rewards, probability, progression, economies, and dominant strategies.

    1.2k GitHub stars~618 tokensUpdated today
    Auto-check passed

  • Manuscript Engagement Analytics

    hashgraph-online/awesome-codex-plugins

    Analyze nonfiction manuscripts for reader engagement signals, including heading-level word counts, slow starts, long slogs, weak takeaway titles, value pacing, beta-reader comment dropoff, and…

    1.2k GitHub stars~875 tokensUpdated today
    Auto-check passed

Categories

Questions about Context Architecture

What does Context Architecture do?

Progressive disclosure architecture for organizing project context as a DAG (directed acyclic graph). Context Architecture is an agent skill from hashgraph-online/awesome-codex-plugins. Progressive disclosure architecture for organizing project context as a DAG (directed acyclic graph).

When should I use Context Architecture?

Context Architecture fits situations like: phrases: context architecture; progressive disclosure; organize context for agents; context directory structure.

How do I install Context Architecture in Claude Code?

Run `npx skills add hashgraph-online/awesome-codex-plugins --skill context-architecture -a claude-code`. Or copy the skill folder (plugins/JuliusBrussee/blueprint/skills/context-architecture in hashgraph-online/awesome-codex-plugins) into .claude/skills/context-architecture in your project. Claude Code loads it when a task matches its description.

How do I install Context Architecture in Codex?

Run `npx skills add hashgraph-online/awesome-codex-plugins --skill context-architecture -a codex`. Or copy the skill folder (plugins/JuliusBrussee/blueprint/skills/context-architecture in hashgraph-online/awesome-codex-plugins) into .agents/skills/context-architecture in your project. Codex loads it when a task matches its description.

Can I use Context Architecture in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add hashgraph-online/awesome-codex-plugins --skill context-architecture -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/context-architecture, .gemini/skills/context-architecture, .github/skills/context-architecture and .opencode/skills/context-architecture in your project.

What does Context Architecture need to run?

Going by SKILL.md and its folder, Context Architecture needs the command-line tools its instructions call (git).

Does Context Architecture access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Context Architecture safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Context Architecture use?

Context Architecture is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Context Architecture use?

About 2.9k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Context Architecture?

Skills that share tags, products or a category with Context Architecture: Using Agent Skills (addyosmani/agent-skills, 103k stars), Claude Reflect (BayramAnnakov/claude-reflect, 1.7k stars), Writing For Agents (bestofjs/bestofjs, 3.1k stars) and Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Context Architecture?

hashgraph-online (a GitHub organization) maintains it in hashgraph-online/awesome-codex-plugins, which has 1,242 GitHub stars. The repository holds 686 skills in this directory. The repository was last updated on October 8, 2026.

Source: hashgraph-online/awesome-codex-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.