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/yuri-semenenko/ai-engineering-workspaceWrote 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/yuri-semenenko/ai-engineering-workspace/start)<a href="https://agentmods.dev/commands/yuri-semenenko/ai-engineering-workspace/start"><img src="https://agentmods.dev/badge/commands/yuri-semenenko/ai-engineering-workspace/start/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/yuri-semenenko/ai-engineering-workspace/start"><img src="https://agentmods.dev/badge/commands/yuri-semenenko/ai-engineering-workspace/start.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 | $0.00016 | $0.00374 |
| Opus 5.5 | $0.00006 | $0.00150 |
| Sonnet 5.5 | $0.00003 | $0.00075 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
start 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 6d 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
Start Prompt
Role: Act as an onboarding guide for the ai-engineering-workspace kit.
Context:
The kit generates a personalized persona from shared templates using a shell
wizard, scripts/create-persona.sh (or scripts/create-persona.ps1 on
Windows). It fills only the identity header (discipline, seniority, workflow,
role, stack, tooling); the methodology canon is fixed and identical for
everyone. This prompt only explains the manual steps.
Task: Explain what the persona wizard produces and give the exact command for the user's operating system so they can run it themselves in a terminal.
Constraints:
- Copy-only. Do not claim to execute the wizard, run shell commands, or modify files.
- Present the command for the user to copy and run manually.
- Do not re-ask the wizard's questions; the wizard owns that flow.
- Keep the corporate-safe posture: no automation, no execution-policy changes, no background agents.
Commands to surface:
- macOS/Linux:
scripts/create-persona.sh(append--defaultsto accept all defaults) - Windows:
powershell -NoProfile -File .\scripts\create-persona.ps1(append-Defaults)
Output Format:
A short explanation that the wizard writes persona/persona.md,
persona/CLAUDE.md, and persona/recommended-skills.md (all gitignored),
followed by the exact command block for the user's OS and a pointer to run the
relevant per-tool installer afterward.
Success Criteria:
- The user knows what the wizard produces and that only the identity header varies.
- The user has the exact command to run manually.
- No claim of automated execution.
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.
- 6d ago First seen · 41 lines · 16 tokens per session scan A 803494a53a4f
start is a command published in the GitHub repository yuri-semenenko/ai-engineering-workspace (4 stars, last pushed 3d ago), licensed MIT. It adds 16 tokens to every session and 374 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 2026-10-31.
start compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| startyuri-semenenko/ai-engineering-workspace | Command | 4 | 3d ago | MIT | A | 16 | GitHub Copilot |
| explainduongductrong/cursor-kit | Command | 23 | 7mo ago | MIT | A | 0 | Claude Code, Cursor |
| merge-conflict-analysisrjmurillo/ai-agents | Command | 49 | yesterday | MIT | A | 0 | GitHub Copilot |
| gofer:check-workspaceeai-support/eai-gofer | Command | 1 | 5d ago | Apache-2.0 | A | 24 | Claude Code |
| start-10-1minicoohei/ai-agent-camp | Command | 347 | 1mo ago | none | A | 2 | Claude Code |
| start-0-8minicoohei/ai-agent-camp | Command | 347 | 1mo ago | none | A | 2 | Claude Code |
| prep-rolefourleafai/clover-public | Command | 8 | 1mo ago | MIT | A | 0 | Claude Code |