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-refactornpx skills add plumbkit/plumb --skill plumb-refactorgit 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 | $0.00022 | $0.01684 |
| Opus 5 | $0.00011 | $0.00842 |
| Sonnet 5 | $0.00004 | $0.00337 |
| Haiku 4.5 | $0.00002 | $0.00168 |
Grade A, and why
plumb-refactor 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When asked to rename, move, or edit code across files in a codebase that has plumb available, use these tools rather than grep/sed or your client's own file-editing tool.
Semantic rename
Use rename_symbol for any identifier rename — workspace-wide, type-aware, updates all definitions and references including imports:
rename_symbol(uri="/path/to/file.go", symbol_name="OldName", new_name="NewName") # preview
rename_symbol(uri="/path/to/file.go", symbol_name="OldName", new_name="NewName", dry_run=false)
Only uri and new_name are required. Identify the symbol by symbol_name — plumb resolves the identifier position for you; raw line/character is the fallback. dry_run defaults to true, so the first call returns a per-file diff to check and a second call with dry_run=false applies it.
Never use find_replace or grep+sed for identifier renames — they miss references across files and break imports.
Atomic cross-file edits
Use transaction_apply for changes spanning multiple files — validates all edits in memory first, then applies them all-or-nothing:
transaction_apply(operations=[
{file_path: "/a.go", edits: [{old_string: "…", new_string: "…"}], expected_mtime: "…"},
{file_path: "/b.go", edits: [{old_string: "…", new_string: "…"}], expected_mtime: "…"},
])
Moving files
Use rename_file for file moves — atomic, refuses to overwrite without overwrite=true:
rename_file(from="/old/path.go", to="/new/path.go")
Single-file edits: read → mtime → edit
- Call
read_fileand copy themtime=value from the response header. - Call
edit_filewithexpected_mtimeset to that value.
Editing several files in the same task no longer needs one read_file call each: read_multiple_files reads up to 20 paths in a single call, and each file's own per-file header carries the mtime/sha256 edit_file needs — the read is recorded per file exactly like read_file, so a later edit_file on any of them works under strict mode with no re-read.
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 · 78 lines · 22 tokens per session scan A 77ec1c48dbc2
plumb-refactor is a skill published in the GitHub repository plumbkit/plumb (4 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 1,684 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
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.
use-modern-go
Use the Modern Go Guidelines CLI whenever writing, modifying, fixing, or refactoring Go code. Apply its version-specific guidance to generated changes.
code-guidelines-go
Go 1.24–1.27 coding guidelines for the dimetron/pi-go AI agent runtime. Use this skill whenever writing, reviewing, or refactoring ANY Go code in pi-go. This covers idiomatic style, error handling, concurrency, project layout, testing (table-driven, fuzz, benchmarks, synctest), new stdlib usage, golangci-lint v2…
go-127
What changed in Go 1.27 (released August 2026) and how it changes the way Go is written in pi-go. Use this skill when writing or reviewing Go that could use a 1.27 feature, when bumping the go directive in go.mod, when a build or test behaves differently after a toolchain upgrade, or when code-guidelines-go points…
bubbletea-testing
Use this skill whenever writing tests for Bubble Tea (charmbracelet/bubbletea) TUI applications in Go. Triggers include any mention of testing Bubble Tea models, teatest, golden file testing for TUIs, testing tea.Cmd or tea.Msg, snapshot testing terminal output, or writing tests for any Go CLI/TUI that uses the Elm…
design-review
Deep design review of Go codebase — naming, structure, consistency, interfaces, error handling. Scores each dimension and provides actionable fixes.