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/rootwarp/claude-code-plugins-monorepo/dev-runnpx skills add rootwarp/claude-code-plugins-monorepo --skill dev-rungit clone --depth 1 https://github.com/rootwarp/claude-code-plugins-monorepoWhat 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 | $0.00057 | $0.03779 |
| Opus 5 | $0.00028 | $0.01889 |
| Sonnet 5 | $0.00011 | $0.00756 |
| Haiku 4.5 | $0.00006 | $0.00378 |
Grade A, and why
dev-run 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 2d 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 — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development Execution Pipeline
You are the engineering team lead. Your job is to drive implementation of development issues by coordinating a code-writer and a code-reviewer. The code-reviewer acts as the review lead — it performs its own code quality review while internally spawning security-auditor and bug-hunter for specialized analysis, merges all findings, and handles merging into develop once everything is resolved.
Team Members
| Agent | Role | Spawned by | Runs |
|---|---|---|---|
| code-writer | Implements issues via TDD in git worktrees | You (team lead) | Sequential (one issue at a time; single stream by default) |
| code-reviewer | Review lead: code quality + orchestrates security/bug review + merges into develop | You (team lead) | After each write/fix cycle |
| security-auditor | Scans for vulnerabilities, OWASP issues | code-reviewer (internal) | Parallel inside code-reviewer |
| bug-hunter | Finds potential bugs, edge cases, race conditions | code-reviewer (internal) | Parallel inside code-reviewer |
Workflow
Stage 1: Load Issues
- Read the user's input:
$ARGUMENTS- If a phase file path is provided, read it to get the issue list
- If
allis specified, Glob forplan/issues/0[1-9]*.mdandplan/issues/[1-9]*.mdto load all phase files - If a specific issue ID is given, find it in the phase files
- If nothing is provided, use AskUserQuestion to ask which phase or issues to implement
- Read the issue file(s) and extract the list of issues with their dependencies and ordering. Stream assignments may be present for multi-stream plans, but treat single-stream (one code-writer at a time) as the default.
- Read supporting documents — Glob for PRD (
plan/prd.md), architecture (plan/architecture.md), project plan (plan/project-plan.md) for context - Create a team using TeamCreate named
dev-run
Stage 2: Plan Execution Order
- Parse issues from the phase file(s), respecting:
- Dependencies — Never start an issue before its blockers are resolved
- Priority — P0 before P1 before P2
- Stream assignments (optional) — Only honor Stream A / Stream B labels if the user has explicitly asked for multi-stream execution. Otherwise treat all issues as a single ordered queue.
- Build the execution queue (default: single stream):
Only build per-stream queues when the user has explicitly opted into multi-stream execution.Issue 1.1 → Issue 1.2 → Issue 1.3 → Issue 1.4 → Issue 1.5 → Issue 1.6 - Present the execution plan to the user and ask for approval before starting
- Create tasks via TaskCreate for every issue in the queue
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.
- 2d ago First seen · 268 lines · 57 tokens per session scan A a735461e4d1b
dev-run is a skill published in the GitHub repository rootwarp/claude-code-plugins-monorepo (2 stars, last pushed 4mo ago), licensed MIT. It adds 57 tokens to every session and 3,779 once invoked, about $0.0003 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
browser-harness-authoring
Use when mapping a repeatable website workflow into a verified Hermes skill so later runs can follow known steps instead of rediscovering the site. Surveys browser compatibility, semantic targets, failure modes, recovery paths, decision gates, and expiry using dummy data and no irreversible submissions.
hermes-agent-skill-authoring
There are two places a SKILL.md can live.
hermes-diagnostic-review
Use when running a read-only diagnostic review of recent Hermes sessions to find recurring mistakes, failed tool calls, and repeated fixes, then propose suggestion-only improvements and reusable skills. Human-gated; never auto-applies.
instruction-eval
Change one condition an agent runs under (instruction text, the reference material instructions point at, MCP tools and permissions, hooks, skill files), then run the same prompts before and after, several times each, to see what actually changes. Produces an HTML report showing both arms' answers side by side. Use…
skill-teilen
Reicht einen Skill, ein Plugin oder eine Vorlage (CLAUDE.md, settings.json, Prompt) in die SKAILE Community Skill-Library ein. Nutzen wenn der User sagt "teile meinen Skill", "teile meine CLAUDE.md", "teile meine Vorlage", "lade meinen Skill in die Community hoch", "reiche meinen Skill ein", "skill teilen" oder "in…
skill-creator
Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating…