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/plumbkit/plumb/plumb-explorenpx skills add plumbkit/plumb --skill plumb-exploregit clone --depth 1 https://github.com/plumbkit/plumbWhat 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 | $0.00015 | $0.01139 |
| Opus 5 | $0.00008 | $0.00570 |
| Sonnet 5 | $0.00003 | $0.00228 |
| Haiku 4.5 | $0.00002 | $0.00114 |
Grade A, and why
plumb-explore 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When asked to understand, explore, or navigate a codebase that has plumb available, work down this ladder rather than reading whole files:
workspace_search → topology / LSP → search_in_files → bounded read_file
Each rung is broader and cheaper than the one below it. Start at the top and drop down only when the note under the rung applies.
Under a lean tool profile several of the tools named below are not advertised. If one of them is not offered to you, use the nearest alternative on the same rung — for rung 0's opening move that is topology_search. Rung 3 is the thinnest: both its tools are hidden under lean, so a lean client falls back to its own native search — though lean read_file still takes pattern, use_regex, and max_matches, which covers scanning a file you have already located without leaving plumb.
0. Ranked discovery — start here
Before reaching for a shell grep, find, or ls, start on this ladder. Those three moves are what it replaces: a conceptual question belongs on this rung, grep belongs on rung 3's search_in_files, and find/ls belong on find_files. Prefer them whenever they are offered to you — they are workspace-bounded, .gitignore-aware, and bounded in output, none of which a shell scan is.
One query across every indexed corpus at once — code symbols, doc sections, and project memories — with each hit labelled by corpus, score, and why it matched.
workspace_search— the opening move for a conceptual question ("where is daemon locking handled?").
Drop down once a hit gives you a symbol or file worth following — or straight away when you already know the name. This rung is approximate by design and never proof of absence.
1. Map (topology) — structure and impact
Topology answers instantly and works even while the language server is warming up.
topology_search— ranked symbol/file discovery.topology_explore— neighbourhood around a named symbol (callers, callees, depth=2).topology_impact— blast radius: what would break if this symbol changes.topology_routes— framework entry points (HTTP handlers, CLI commands).file_outline— file shape (signatures, bodies collapsed) in ~200 tokens.read_symbol— source of one named symbol without reading the whole file.
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 · 63 lines · 15 tokens per session scan A a3b6de75eb97
plumb-explore is a skill published in the GitHub repository plumbkit/plumb (4 stars, last pushed 2d ago), licensed MIT. It adds 15 tokens to every session and 1,139 once invoked, about $0.0001 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
fleet-manager
Use when managing, triaging, restarting, escalating, or summarizing Codewhale Pod runs and workers.
skill-creator
Create or improve codewhale skills. Use when the user wants a new skill, wants to update an existing skill, or needs guidance on when a skill should be a skill versus MCP, hooks, tools, or a plugin scaffold.
mcp-builder
Design, build, configure, or debug Model Context Protocol servers for codewhale, including stdio and HTTP/SSE transports.
extension-creator
Create, scaffold, customize, validate, and locally test Qwen Code extensions. Use when the user wants a new Qwen Code extension, needs help choosing an extension template, wants to add QWEN.md context, commands, skills, agents, MCP servers, settings, hooks, channels, or LSP servers, or asks how to link and test an…
mcp-discovery
Prefer a matching zero-environment local MCP server for specialized tasks, even when built-in shell commands or custom code could also solve them.
google-agents-cli-observability
This skill should be used when the user wants to "set up tracing", "monitor my agent", "configure logging", "add observability", "debug production traffic", or needs guidance on monitoring deployed agents, including ADK (Agent Development Kit) agents. Covers Cloud Trace, prompt-response logging, BigQuery Agent…