Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/thelobbi/claude/command-templategit clone --depth 1 https://github.com/TheLobbi/claudeWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00311 |
| Opus 5 | $0.00000 | $0.00156 |
| Sonnet 5 | $0.00000 | $0.00062 |
| Haiku 4.5 | $0.00000 | $0.00031 |
Grade A, and why
.command-template scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{{command-name}}
Usage: /{{command-name}} [args]
Context Budget: 500 tokens max (command file only)
Category: {{category}}
context_budget: 500 strict_enforcement: true forbidden_files:
- commands.index.json
- CLAUDE.full.md
- agents.index.json
- Any related command files
Description
{{brief-description}}
Usage
/{{command-name}} [required-args] [optional-args]
Examples
/{{command-name}} example
Implementation
{{command-logic-here}}
External Resources (Load On-Demand)
DO NOT load these in command context. Load via MCP when needed:
- Agent definitions:
mcp__obsidian__get_file_contents("System/Claude-Instructions/Agent-Categories.md") - Registry data: Query
.claude/registry/commands.index.jsonfor metadata only - Full documentation: Load from Obsidian vault when needed
- Related commands: Don't load unless explicitly referenced
Context Optimization
This command follows minimal context loading:
- ✅ Loads only this file (~200-500 tokens)
- ✅ References minimal CLAUDE.md (~300 tokens)
- ❌ Does NOT load full registry
- ❌ Does NOT load full documentation
- ❌ Does NOT load all agent definitions
Total context: ~500-800 tokens (command file + CLAUDE.md only)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 53 lines · 0 tokens per session scan A 194550aba3c7
.command-template is a command published in the GitHub repository TheLobbi/claude (21 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 311 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.