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.
git clone --depth 1 https://github.com/notque/vexjoy-agentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/notque/vexjoy-agent/d)<a href="https://agentmods.dev/commands/notque/vexjoy-agent/d"><img src="https://agentmods.dev/badge/commands/notque/vexjoy-agent/d/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/notque/vexjoy-agent/d"><img src="https://agentmods.dev/badge/commands/notque/vexjoy-agent/d.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00030 | $0.00575 |
| Opus 5.5 | $0.00012 | $0.00230 |
| Sonnet 5.5 | $0.00006 | $0.00115 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
d 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/d - Jev-validated Router
Route user requests with /do's rule text and manifest, then use Jev to
attach domain skills and check that the restated outcome survives the route.
Use /d to A/B-test against /do; use /do for normal work.
Instructions
Call the Skill tool with d. Follow its classify, decide, enhance, and
execute phases.
Base directory: $CLAUDE_PROJECT_DIR or the current working directory
Skill file: skills/meta/d/SKILL.md
Phase 1: CLASSIFY — scripts/jev-route.py runs the force-route guard and
one Jev attachment evaluation. You pick the agent, skill, and pipeline with
/do's rules (scripts/print-route-rules.py) and the routing manifest, then
jev-route.py --finalize validates the pick and adds the attachments.
Phase 2: ALIGN INTENT — MANDATORY before any banner or dispatch. Write
PROPOSED_INTENT for the finalized route, run jev-intent-align.py on it.
Phase 3: DECIDE — Show the finalized route. Display the routing banner
only after Phase 2 completes.
Phase 4: ENHANCE — Map stack signals to concrete stack entries.
Phase 5: EXECUTE — Same Task Spec + build-dispatch.py contract /do
uses, reused unmodified.
The routing banner MUST include the Phase 2 intent alignment result:
===================================================================
ROUTING (/d): [brief summary]
===================================================================
Intent (/d):
-> Restated: [PROPOSED_INTENT]
-> Alignment: [aligned|review|unavailable] [— issues, if any]
Selected:
-> Agent: [name] - [reasoning]
-> Skill: [name] - [reasoning]
-> Source: [session|pre-route-force] (confidence: [level])
Invoking...
===================================================================
A banner printed without the Intent block means Phase 2 was skipped — that is not allowed.
For the full design (why /d exists as a separate command, the
request/response contract, measured eval results), read
skills/meta/d/SKILL.md and
skills/meta/d/references/jev-classifier-design.md.
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.
- today Changed · -5 lines · -3 tokens per session 9fcb4a9440da
- 24d ago Changed · +9 lines 60a39f889e90
- 29d ago First seen · 58 lines · 33 tokens per session scan A 119ae83d3555
d is a command published in the GitHub repository notque/vexjoy-agent (442 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 575 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-18.
Other commands, from other repositories
ui5-version
Display UI5 version information, support status, release notes, and upgrade paths.
audit-checklist
Perform an internal audit, review controls, or prepare for an external financial audit.
plan-localization
Plan localisation covering extraction, translation workflow, and the layout and format issues that follow.
persuasion
/volumes/vixinssd/wizardsoftheghosts/generated/openclaw/persuasion/SKILL.md.
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.