Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →hashgraph-online/context-architecture
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"
Passed 20 of 22 test cases with the skill, and 5 of 22 without it.
and 21 more in the full report
16 fixed4 passed either way1 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 16 test cases the skill fixed. Same model, same prompt, with and without the skill.
When tracking implementation progress in context/impl/, at what line length threshold should tracking logs be compacted, and where are archived records stored?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies 500 lines as the threshold for compacting tracking log files. | Missed | Passed |
| Moves compacted log entries into context/impl/archive/. | Passed | Passed |
The instructions your model reads when the skill loads.
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.
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.
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."
test cases passed, vs 5 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.