count-registry
Provides canonical entity counts from count-manifest.json. Use when agents need to reference how many agents, skills, instructions, or validators exist. Prevents hard-coded counts. WHEN: agent count, skill count, how many agents, how many skills, entity inventory, project statistics.
90
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Count Registry
Single source of truth for project entity counts.
Source of Truth
All counts live in tools/registry/count-manifest.json. Validators auto-compute actual
values from filesystem globs. No other file should hard-code these numbers.
How to Reference Counts
When generating documentation or artifacts that mention entity quantities:
- Prefer descriptive language — "a set of specialized agents and subagents", "the full skill catalog", "the multi-step workflow"
- When exact numbers are needed, read
tools/registry/count-manifest.jsonand state the number with a parenthetical source: "16 primary agents (per count-manifest.json)" - Never hard-code a count into prose that will be committed to the repo
Canonical Phrasing Patterns
| Entity | Canonical phrase |
|---|---|
| Agents | "specialized agents and subagents" |
| Skills | "the skill catalog" or "available skills" |
| Instructions | "instruction files" |
| Validators | "the validation suite" |
| Workflow steps | "the multi-step workflow" (never count steps — Step 3.5 makes any number ambiguous) |
| MCP tools | "pricing query tools" |
| VS Code extensions | "pre-installed extensions" |
Computed Entities
The manifest defines computed_from globs for each entity. The
validate-no-hardcoded-counts.mjs validator resolves these globs against
the filesystem and reports any drift between documented and actual counts.
Entities with a static value field (e.g., golden principles = 10) are
genuinely fixed and exempt from the no-hard-coding rule.
- Repository
- jonathan-vella/azure-agentic-infraops
- Commit
ec7b8ff
- Last updated
- Created
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.