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-testingnpx skills add plumbkit/plumb --skill plumb-testinggit 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 | $0.00040 | $0.01064 |
| Opus 5 | $0.00020 | $0.00532 |
| Sonnet 5 | $0.00008 | $0.00213 |
| Haiku 4.5 | $0.00004 | $0.00106 |
Grade A, and why
plumb-testing 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
After changing code in a codebase that has plumb available, verify the change before calling it done: ask which tests it touches, run those, and confirm the code still compiles — rather than guessing, or paying for the whole suite every time.
1. Ask which tests the change affects
topology_affected traverses inward dependency edges from what you changed and adds the tests co-located with the affected files:
topology_affected(files=["internal/tools/edit_file.go"])
topology_affected(symbols=["applyEdits"])
It is biased toward recall — a missed test is worse than an extra one — so every result carries a confidence and the reason it was flagged. Read those labels; they decide the last section.
2. Run what it named
run_task runs the project's stored [tasks.<lang>] command with no shell and bounded output:
run_task(slot="test") # the stored test command, whole
run_task(slot="verify") # build, then test
slot is build / lint / test / e2e / verify. target fills a {target} placeholder with one shell-safe argument, and the shipped go, python and rust test defaults now carry a defaulted one (go test {target:./...}, pytest {target:}, cargo test {target:}), so scoping works on an unmodified install and a bare run_task(slot="test") still runs everything. npm test, swift test and zig build test have no placeholder, because those runners scope through flags whose spelling depends on the project — a target passed to a command without a placeholder is refused.
When the command takes a positional path, topology_affected hands you the target already shaped for it, relative to [tasks.<lang>].working_dir, so the two compose directly:
run_task(slot="test", target="./internal/config/...") # a row from topology_affected, verbatim
Where no target can be spelled — a runner that scopes by test name, a project-specific flag, or a package outside the command's working_dir — topology_affected names the directory and guesses no command. Use your own runner there, but keep the scope it gave you. When the project configures no command for the slot, use the client's runner too — but keep the scope topology_affected gave you. A project-supplied command that is not yet trusted is refused with a pointer to plumb trust: that is a gate, not a missing command — surface it rather than shelling around it.
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 · 50 lines · 40 tokens per session scan A 5756250ce530
plumb-testing is a skill published in the GitHub repository plumbkit/plumb (4 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 1,064 once invoked, about $0.0002 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
nim-mcp-tools
Use for Nim symbol navigation, diagnostics, and type resolution. MANDATORY: Use specialized MCP tools (nimFindSymbols, nimFindReferences, nimListSymbols, nimCheckFile, nimCheckProject, nimFindTypeDefinition) first; fall back to grep only on error or user confirmation.
yaml
Validate and understand schema-backed YAML (Kubernetes, Flux, and JSON-Schema configs) with the yayamlls language server. Use when editing or reviewing .yaml/.yml files, diagnosing schema validation errors, configuring .yayamlls.yaml, suppressing a diagnostic, or working with Flux HelmRelease / Kustomization rendering.
lsp-config
This skill should be used when the user asks about "LSP configuration", "language server setup", "adding LSP to Claude Code", "mason config import", "lspconfig migration", "lspctl plugin", or discusses Claude Code LSP integration and troubleshooting.
batch
Execute batch operations on multiple files in parallel. Automatically discovers files, splits into chunks, and processes with parallel worker agents. Use /batch followed by operation and file pattern.
fleet-manager
Use when managing, triaging, restarting, escalating, or summarizing Codewhale Pod runs and workers.
gh-assign-issues
Use to assign GitHub issues to a milestone and/or owners in bulk, verifying each.