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/notque/vexjoy-agent/dogit clone --depth 1 https://github.com/notque/vexjoy-agentWhat 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 | $0.00013 | $0.00346 |
| Opus 5 | $0.00006 | $0.00173 |
| Sonnet 5 | $0.00003 | $0.00069 |
| Haiku 4.5 | $0.00001 | $0.00035 |
Grade A, and why
do 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 2d ago.
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
/do - Smart Router
Route user requests to the correct agent + skill combination.
Instructions
Call the Skill tool with do. Follow its classification, routing, enhancement, and execution phases.
Base directory: $CLAUDE_PROJECT_DIR or the current working directory
Skill file: skills/meta/do/SKILL.md
Phase 1: CLASSIFY — Assess complexity, check parallel patterns
Phase 2: ROUTE — Select agent + skill, display routing banner
Phase 3: ENHANCE — Stack retro knowledge, anti-rationalization, parallel reviewers
Phase 4: EXECUTE — Create the plan and dispatch through build-dispatch.py. The builder emits Call the Skill tool with \skill-name`.` once for the primary skill and each callable stack skill.
Learning capture runs automatically via hooks — no router step (see "Learning Capture" in the skill).
The routing banner MUST be the first visible output:
===================================================================
ROUTING: [brief summary]
===================================================================
Selected:
-> Agent: [name]
-> Skill: [name]
Invoking...
===================================================================
For complete routing, force-route triggers, and domain agent mappings, read skills/meta/do/SKILL.md; the routing manifest is generated by scripts/routing-manifest.py from the INDEX files (single source of truth).
ARGUMENTS: $ARGUMENTS
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.
- 2d ago First seen · 44 lines · 13 tokens per session scan A 4fcad962fc0b
do is a command published in the GitHub repository notque/vexjoy-agent (417 stars, last pushed 2d ago), licensed MIT. It adds 13 tokens to every session and 346 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-30.
Other commands, from other repositories
new-skill
Scaffold a new hr- skill directory with SKILL.md, content/, and examples/ templates.
advisor
Advisory gate for triage or plan decisions. Spawns a second-opinion agent that challenges assumptions, surfaces risks, and proposes alternatives before the decision commits. Based on Anthropic advisor tool pattern.
review-sdk-app
Review and validate a Claude Agent SDK application against best practices.
audit-checklist
Perform an internal audit, review controls, or prepare for an external financial audit.
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.