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/alexmond/alexmskills/dev-crewnpx skills add alexmond/alexmskills --skill dev-crewgit clone --depth 1 https://github.com/alexmond/alexmskillsWrote 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/skills/alexmond/alexmskills/dev-crew)<a href="https://agentmods.dev/skills/alexmond/alexmskills/dev-crew"><img src="https://agentmods.dev/badge/skills/alexmond/alexmskills/dev-crew.svg" alt="Measured on agentmods" 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 | $0.00159 | $0.05107 |
| Opus 5 | $0.00079 | $0.02554 |
| Sonnet 5 | $0.00032 | $0.01021 |
| Haiku 4.5 | $0.00016 | $0.00511 |
Grade A, and why
dev-crew 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 5d 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 — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dev-crew
Try it:
/dev-crew:dev-crew add rate limiting to the login endpoint— or say "run the crew on this feature".
A self-evolving software delivery crew. The main session acts as the conductor: it selects which roles a task needs, delegates each phase to a role subagent (which carries its own model and tool scope), passes work between roles through shared handoff files, gates risky transitions, and writes back what it learned so the crew gets better-tuned to this codebase over time.
This is the execution counterpart to brainstorm-panel. Panel converges on
what to build; crew runs the building. They compose — a panel outcome can be
handed straight to the crew as the task brief.
Who orchestrates
The orchestrator is the main Claude Code session with this skill loaded — not a subagent. The skill is instructions that make that session act as the conductor: read context, name the category, propose and run the roster, delegate each phase to a role subagent via the Task tool, receive their file handoffs, enforce the gates, write the log and graduation.
Roles report up to the conductor and hand off to each other only through files — they never call each other directly. The conductor's model and each role's model are independent: a subagent runs on its own frontmatter model and inherits nothing of the conductor's context or system prompt.
Run the conductor on opus (or sonnet to economize).
Files this skill owns
<repo>/.claude/roles/crew.md— the canonical role registry: role -> model -> tools -> status -> learnings. Read this first, every run. The conductor creates it on first run in a repo by copying this skill's shippedroles.mdseed. It lives in the repo — not next to the skill — because a marketplace-installed plugin's skill dir is a read-only cache, and.claude/roles/is the shared home (brainstorm-panel keeps its registry at.claude/roles/panel.md; optional shared core role files.claude/roles/<role>.mdmay exist via therolesplugin).<repo>/.claude/dev-crew/log.md— append-only run log; the substrate the learning loop reads from. The conductor seeds it on first run from this skill's shippedlog.md(a read-only schema seed — never write to the installed copy). Everylog.mdreference below means this repo file.templates/role-template.md— scaffold for minting a new role subagent.templates/CLAUDE-md-block.md— the## Dev crewblock graduated into a repo.- Per-run scratch lives in
<repo>/.claude/dev-crew/runs/<run-id>/(handoff files, never committed unless the user asks).
What ships with it
6 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.
- 5d ago First seen · 351 lines · 159 tokens per session scan A 3f0098682876
dev-crew is a skill published in the GitHub repository alexmond/alexmskills (6 stars, last pushed today), licensed MIT. It adds 159 tokens to every session and 5,107 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…