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 skills/deevsdeevs/agent-system/dev-expertsnpx skills add DeevsDeevs/agent-system --skill dev-expertsgit clone --depth 1 https://github.com/DeevsDeevs/agent-systemWhat 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 | $0.00091 | $0.00405 |
| Opus 5 | $0.00046 | $0.00202 |
| Sonnet 5 | $0.00018 | $0.00081 |
| Haiku 4.5 | $0.00009 | $0.00040 |
Grade A, and why
dev-experts 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 3d 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
Dev Experts
Use a single skill with persona selection. If the user specifies a persona name, use that persona. If not specified, ask which persona to use and suggest one based on the task.
Persona Map
architect→agents/architect.mddevops→agents/devops.mdrust-dev→agents/rust-dev.mdpython-dev→agents/python-dev.mdcpp-dev→agents/cpp-dev.mdreviewer→agents/reviewer.mdtester→agents/tester.md
Workflow
- Read
README.mdfor the global flow and constraints. - Read the selected persona file and follow its workflow verbatim.
- Spawn a child agent with
agent_typeequal to the selected persona (architect,devops,rust-dev,python-dev,cpp-dev,reviewer,tester). - Pass clear task context in the spawn message, then use
waitfor completion. - If needed, send targeted follow-ups with
send_input, thenwaitagain. - Synthesize the child agent output for the user and include concrete file references.
- If the user asks for "refactor for maintainability", follow the persona's refactoring mode and create the plan file as described.
- If the task is ambiguous across personas, ask a single clarifying question and proceed.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 30 lines · 91 tokens per session scan A 803546d92343
dev-experts is a skill published in the GitHub repository DeevsDeevs/agent-system (40 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 91 tokens to every session and 405 once invoked, about $0.0005 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 skills, from other repositories
ask
Process-first advisor routing for Claude, Codex, Gemini, Antigravity, Grok, or Cursor via omc ask, with artifact capture and no raw CLI assembly.
external-context
Invoke parallel document-specialist agents for external web searches and documentation lookup.
reflect
Review recent work, find repeated workflow patterns, and suggest reusable skills, agents, commands, config changes, or playbooks. Use when the user asks to learn from past sessions, improve recurring workflows, or identify what should be turned into reusable agent instructions.
codemap
Generate comprehensive hierarchical codemaps for UNFAMILIAR repositories. Expensive operation - only use when explicitly asked for codebase documentation or initial repository mapping.
scientific-schematics
Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.1 Pro Preview for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways…
openpets
Use when the user asks to install, configure, verify, troubleshoot, or understand OpenPets; install or select a pet; connect Claude Code, OpenCode, Cursor, Codex, or MCP clients; configure a project to use a specific pet; or debug openpetsstatus, openpetsreact, or openpetssay.