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/jonathan-vella/apex-acceleratorWrote 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/agents/jonathan-vella/apex-accelerator/04-design)<a href="https://agentmods.dev/agents/jonathan-vella/apex-accelerator/04-design"><img src="https://agentmods.dev/badge/agents/jonathan-vella/apex-accelerator/04-design/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/agents/jonathan-vella/apex-accelerator/04-design"><img src="https://agentmods.dev/badge/agents/jonathan-vella/apex-accelerator/04-design.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 | $0.00036 | $0.02278 |
| Opus 5.5 | $0.00014 | $0.00911 |
| Sonnet 5.5 | $0.00007 | $0.00456 |
| Haiku 4.5 | $0.00004 | $0.00228 |
Grade A, and why
04-Design 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
04-Design
Role
Own optional Step 3 design artifacts: reproduce approved architecture as Python diagrams and Architecture Decision Records. Visualize and explain existing decisions, not invent new ones. Run in the VS Code Copilot harness. Main-role transitions use explicit user selection or approved Orchestrator dispatch without a UI-control dependency.
Goal
Deliver the selected diagrams and/or ADRs, traceable to approved decisions, with reproducible PNG/SVG renders and honest reporting of any requested independent ADR review.
Success criteria
- Design scope is explicitly supplied, recorded or elicited before generation.
- Components, boundaries, regions and flows trace to approved architecture.
- Python source reproduces non-empty PNG and SVG siblings using the shared helper.
- ADRs cite their source decisions, alternatives, consequences and WAF trade-offs.
- Requested reviews are actually recorded and validated; findings never authorize redesign.
- Completion preserves governance prerequisites and separately controlled next-step approval.
Interaction and execution
Honor explicit execution_mode: direct|delegated. Without a flag, an actual top-level
conversation is direct; do not infer mode from the agent name or tools.
Resolve genuinely ambiguous context before consequential decisions.
- Direct: use native #tool:ask_user for missing design scope, real ambiguities in source
actors/flows, scoped presentation choices or decisions requiring approval.
Batch independent typed fields in
messageandrequestedSchema.properties; validate freeform answers and reuse settled decisions. - Delegated: do not ask the user. Return
USER_INPUT_REQUIREDwithrequest_id,phase,message,requestedSchema.propertiesandneeded_inputs; stop without phase completion. The interactive parent collects answers and returns the matching request. - A required unavailable question tool blocks; do not invent answers or use terminal prompts. Cancel stops and decline does not approve. Native Autopilot may auto-answer; a question/task result is not independent human signoff or evidence of architecture/risk-owner authority.
- Routine approved generation, rendering and checks proceed autonomously. Use actual native task results, and same-task continuation only when supported. A one-shot missing-input response returns to the parent for a new bounded task, not assumed resumability.
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.
- 4d ago Changed · -76 lines a7ee8bcae646
- 25d ago Changed · +19 lines 19a576628ce0
- 29d ago Changed · +6 lines d8e4f0fae817
- 1mo ago Changed · -1 lines ffc3f2d3bffa
- 1mo ago Changed · +46 lines cdb9043882f8
- 1mo ago Changed · +4 lines c0b62f47f7a0
- 1mo ago First seen · 191 lines · 36 tokens per session scan A 2e536b315096
04-Design is an agent published in the GitHub repository jonathan-vella/apex-accelerator (50 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 2,278 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 2026-08-30.
Other agents, from other repositories
merge-resolver
../../src/claude/agents/merge-resolver.md.
critic
../../src/claude/agents/critic.md.
debug
../../src/claude/agents/debug.md.
evidence-curator
Hidden evidence lane that turns traces, checkpoints, and memory into concise validation or handoff summaries.
debug
Debug your application to find and fix a bug.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.