Claude Code Skills Marketplace is a collection and marketplace of skills, plugins, agents, and instructions that extend Claude Code with specialized development workflows. It is for developers who want to install existing workflows or create, validate, and package their own Claude Code skills.
Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add daymade/claude-code-skills/plugin install daymade-claude-codeWrote 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/daymade/claude-code-skills/claude-code-ops-router)<a href="https://agentmods.dev/skills/daymade/claude-code-skills/claude-code-ops-router"><img src="https://agentmods.dev/badge/skills/daymade/claude-code-skills/claude-code-ops-router/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/daymade/claude-code-skills/claude-code-ops-router"><img src="https://agentmods.dev/badge/skills/daymade/claude-code-skills/claude-code-ops-router.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 | $0.00075 | $0.00862 |
| Opus 5.5 | $0.00030 | $0.00345 |
| Sonnet 5.5 | $0.00015 | $0.00172 |
| Haiku 4.5 | $0.00007 | $0.00086 |
Grade A, and why
claude-code-ops-router 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 16d 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
Claude Code operations router
Choose the one specialist that owns the requested operation. Locate this
loaded claude-code-ops-router/SKILL.md in the active catalog or invocation,
follow symlinks to its canonical path, and verify its parent is
claude-code-ops-router. Its parent's parent is the suite root. Resolve the
selected relative path against that directory and verify it is a direct
sibling SKILL.md inside the root. Never anchor resolution to the task's
working directory or a remembered plugin cache. ${CLAUDE_PLUGIN_ROOT} may
help in Claude Code, but it is absent in Codex. Stop if the active router path
cannot be identified unambiguously.
Read the selected child SKILL.md in full before acting. Continue a
truncated read and load its task-required references. Its instructions,
scripts, and assets remain installed; only its automatic catalog entry is
hidden. Claude users retain the original manual commands named by each child's
frontmatter. The export-repair directory claude-export-txt-better exposes
/daymade-claude-code:fixing-claude-export-conversations.
| Requested operation | Read this exact file |
|---|---|
| Repair a Claude Code plugin or Skill that is installed but missing, disabled, or failing to activate | ../claude-skills-troubleshooting/SKILL.md |
| Install, change, or repair the Claude Code statusline | ../statusline-generator/SKILL.md |
Repair line wrapping, tables, paths, or tool output in an exported Claude Code .txt conversation |
../claude-export-txt-better/SKILL.md |
| Create or maintain a Claude Code plugin marketplace, suite membership, or marketplace manifest | ../marketplace-dev/SKILL.md |
| Analyze Claude Code/Desktop Code token use, cost, cache, quota burn, or 5-hour blocks | ../claude-usage-analyst/SKILL.md |
Configure isolated Claude Code model-provider profiles, aliases, source-backed Claude/Codex Skill activation, or context-window size; reduce preloaded MCP schema context after active-profile and provider checks, or safely suppress selected MCP servers; repair early compaction, [1m] display, or CLAUDE_CODE_MAX_CONTEXT_TOKENS |
../claude-switch-models-setup/SKILL.md |
| Migrate existing Claude personal memory into tool-agnostic AGENTS.md reference documents, or retire a project's auto memory so documents own everything it held | ../claude-migrate-memory-to-doc/SKILL.md |
| Set a one-shot local ping after a Claude subscription quota reset to start the next usage window | ../claude-code-ping-start-5h-quota/SKILL.md |
Route by the requested operation, not by the word “Claude.” For example,
usage diagnosis selects claude-usage-analyst; a requested future reset ping
selects claude-code-ping-start-5h-quota. A Skill count, discovery-policy
audit, or cold-catalog change belongs to skill-governance when installed;
plugin activation repair is the narrower troubleshooting row here.
This router does not replace the direct entries for conversation-history reading and continuation, prior-work retrieval, hooks, CLAUDE.md editing, Lark, Claude.ai web-conversation export, terminal color screenshots, relayed web-search repair, or technology selection. Do not use it to handle those requests merely because Claude Code is mentioned. Selecting a child does not authorize an external installation, credential operation, or scheduled job; follow the selected child's instructions and the user's authorization.
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.
- 16d ago Changed · +4 tokens per session 9198b9b8f4af
- 1mo ago First seen · 53 lines · 71 tokens per session scan A 297ce968c0c4
claude-code-ops-router is a skill published in the GitHub repository daymade/claude-code-skills (1,516 stars, last pushed yesterday), licensed MIT. It adds 75 tokens to every session and 862 once invoked, about $0.0003 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 2026-09-25.
claude-code-ops-router compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| claude-code-ops-routerdaymade/claude-code-skills | Skill | 1.5k | yesterday | MIT | A | 75 | Claude Code |
| orbit-notionnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 117 | Claude Code, Codex |
| agentmailpaperclipai/paperclip | Skill | 111k | yesterday | MIT | A | 30 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| rowboat-spacesrowboatlabs/rowboat | Skill | 18k | yesterday | Apache-2.0 | A | 60 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 33 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |