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 skills add hiroro-work/claude-plugins --skill dev-workflowgit clone --depth 1 https://github.com/hiroro-work/claude-pluginsWrote 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/hiroro-work/claude-plugins/dev-workflow)<a href="https://agentmods.dev/skills/hiroro-work/claude-plugins/dev-workflow"><img src="https://agentmods.dev/badge/skills/hiroro-work/claude-plugins/dev-workflow/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/skills/hiroro-work/claude-plugins/dev-workflow"><img src="https://agentmods.dev/badge/skills/hiroro-work/claude-plugins/dev-workflow.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 | $0.00102 | $0.07324 |
| Opus 5.5 | $0.00041 | $0.02930 |
| Sonnet 5.5 | $0.00020 | $0.01465 |
| Haiku 4.5 | $0.00010 | $0.00732 |
Grade D, and why
dev-workflow scanned grade D with 2 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`language` resolves as: merged settings → `language` in `~/.claude/settings.json` → `ja`. Headings, phase names, commit messages, diffs, and paths stay as written; prose follows it, in plain words, one claim per sentence Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
allowed-tools: Agent, Read, Write, Edit, Glob, Grep, TaskCreate, TaskUpdate, TaskList, AskUserQuestion, Artifact, Skill(artifact-design), Skill(ask-peer), Skill(ask-claude), Skill(ask-codex), Skill(ask-gemini), Skill(ask The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
27 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.
- .claude-plugin/plugin.json 638 B
- README.md 9.7 KB
- references/commits.md 7.4 KB
- references/crit-gate.md 4.1 KB
- references/decomposition-state.md 3.3 KB
- references/decomposition.md 2.4 KB
- references/init-mode.md 2.6 KB
- references/mob-mode.md 13 KB
- references/plan-approval.md 5.0 KB
- references/plan-artifact.md 3.3 KB
- references/plan-format.md 3.5 KB
- references/review-launch.md 2.1 KB
- references/self-retrospective.md 5.3 KB
- references/snapshots.md 5.6 KB
- references/tiers.md 1.8 KB
- references/timing.md 2.6 KB
- references/workability.md 4.1 KB
- scripts/absorb/attribute.mjs 8.0 KB runs code
- scripts/plan-review/export-plan-html.mjs 6.5 KB runs code
- scripts/plan-review/public/index.html 21 KB
- scripts/plan-review/public/plan-parse.mjs 16 KB runs code
- scripts/plan-review/public/plan-render.mjs 21 KB runs code
- scripts/plan-review/public/plan-view.css 28 KB
- scripts/plan-review/serve.mjs 11 KB runs code
- scripts/retro/session-text.mjs 3.8 KB runs code
- scripts/timing/mark.mjs 2.8 KB runs code
- scripts/timing/report.mjs 3.4 KB runs code
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 Changed 826c19abe230
- 8d ago Changed · -14 tokens per session c7d1eec96788
- 27d ago Changed 099f8d98ab9f
- 1mo ago Changed 63def33b4671
- 1mo ago Changed · +8 lines 99577c85893e
- 1mo ago Changed · -2 lines 0210d13b4356
- 1mo ago Changed 761e5aba3513
- 1mo ago Changed · +1 lines 5abc4ada4f38
- 1mo ago Changed · -204 lines · +44 tokens per session scan B → D 2eb85ce98195
- 1mo ago First seen · 433 lines · 72 tokens per session scan B 516129466270
dev-workflow is a skill published in the GitHub repository hiroro-work/claude-plugins (47 stars, last pushed today), with no licence file. It adds 102 tokens to every session and 7,324 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
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…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…