intent-layer▌
crafter-station/skills · updated Apr 8, 2026
Hierarchical AGENTS.md infrastructure so agents navigate codebases like senior engineers.
Intent Layer
Hierarchical AGENTS.md infrastructure so agents navigate codebases like senior engineers.
Core Principle
Only ONE root context file. CLAUDE.md and AGENTS.md should NOT coexist at project root. Child AGENTS.md in subdirectories are encouraged for complex subsystems.
Workflow
1. Detect state
scripts/detect_state.sh /path/to/project
→ Returns: none | partial | complete
2. Route
none/partial → Initial setup (steps 3-5)
complete → Maintenance (step 6)
3. Measure [gate - show table first]
scripts/analyze_structure.sh /path/to/project
scripts/estimate_tokens.sh /path/to/each/source/dir
4. Decide
No root file → Ask: CLAUDE.md or AGENTS.md?
Has root file → Add Intent Layer section + child nodes if needed
5. Execute
Use references/templates.md for structure
Use references/node-examples.md for real-world patterns
Validate: one root, READ-FIRST directive, <4k tokens per node
6. Maintenance mode (when state=complete)
Ask user:
a) Audit nodes → Use references/capture-protocol.md for SME questions
b) Find candidates → Re-measure tokens, suggest new nodes
c) Both
When to Create Child Nodes
| Signal | Action |
|---|---|
| >20k tokens in directory | Create AGENTS.md |
| Responsibility shift | Create AGENTS.md |
| Hidden contracts/invariants | Document in nearest ancestor |
| Cross-cutting concern | Place at LCA |
Do NOT create for: every directory, simple utilities, test folders (unless complex).
Capture Questions
When documenting existing code, ask:
- What does this area own? What's out of scope?
- What invariants must never be violated?
- What repeatedly confuses new engineers?
- What patterns should always be followed?
Resources
Scripts:
scripts/detect_state.sh- Check Intent Layer state (none/partial/complete)scripts/analyze_structure.sh- Find semantic boundariesscripts/estimate_tokens.sh- Measure directory complexity
References:
references/templates.md- Root and child node templatesreferences/node-examples.md- Real-world examplesreferences/capture-protocol.md- SME interview protocol
Discussion
Product Hunt–style comments (not star reviews)- No comments yet — start the thread.
Ratings
4.6★★★★★70 reviews- ★★★★★Harper Shah· Dec 28, 2024
Useful defaults in intent-layer — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
- ★★★★★Hana Abbas· Dec 28, 2024
intent-layer has been reliable in day-to-day use. Documentation quality is above average for community skills.
- ★★★★★Hana Chawla· Dec 28, 2024
Registry listing for intent-layer matched our evaluation — installs cleanly and behaves as described in the markdown.
- ★★★★★Anaya Malhotra· Dec 24, 2024
We added intent-layer from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
- ★★★★★Ganesh Mohane· Dec 4, 2024
I recommend intent-layer for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
- ★★★★★Sofia Robinson· Dec 4, 2024
intent-layer fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
- ★★★★★Rahul Santra· Nov 23, 2024
intent-layer fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
- ★★★★★Advait Nasser· Nov 23, 2024
I recommend intent-layer for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
- ★★★★★Liam Thomas· Nov 19, 2024
intent-layer is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
- ★★★★★Liam Haddad· Nov 19, 2024
Solid pick for teams standardizing on skills: intent-layer is focused, and the summary matches what you get after install.
showing 1-10 of 70