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 skills add plumbkit/plumb --skill plumb-minimal-changegit clone --depth 1 https://github.com/plumbkit/plumbWrote 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/plumbkit/plumb/plumb-minimal-change)<a href="https://agentmods.dev/skills/plumbkit/plumb/plumb-minimal-change"><img src="https://agentmods.dev/badge/skills/plumbkit/plumb/plumb-minimal-change.svg" alt="Measured on agentmods" 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 | $0.00022 | $0.00590 |
| Opus 5 | $0.00011 | $0.00295 |
| Sonnet 5 | $0.00004 | $0.00118 |
| Haiku 4.5 | $0.00002 | $0.00059 |
Grade A, and why
plumb-minimal-change 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 7d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Before writing non-trivial code in a codebase that has plumb available, work through this ladder. Each step is evidence, not vibes — cite what the tools actually returned.
1. Trace the flow first
workspace_search / topology_search / file_outline / read_symbol the relevant area before editing anything. Understand what's already there.
2. Ask if this needs code at all
A doc update, a config change, or an existing flag may satisfy the request. Check before reaching for an editor.
3. Search for existing helpers before writing new ones
workspace_search and workspace_symbols for a function/type that already does this; check memory hints (relevant_memories) for prior art or a declined approach.
4. For bug fixes, find every caller
find_references / topology_impact on the broken symbol. Fix the shared root cause once, not each call site separately.
5. Prefer what's already there
Stdlib, platform, or an already-installed dependency beats a new dependency or a custom framework.
6. Use the smallest edit surface that preserves behaviour
Symbol edits (replace_symbol_body, insert_before_symbol/insert_after_symbol, move_symbol) over full-file rewrites. Deletion over new abstraction when it's safe to delete.
7. Verify proportionally
topology_affected to pick the focused tests; run_task for the smallest relevant check. Run the broader verify before claiming done only when the change's scope warrants it.
Before committing, minimal_diff_review(mode="changed") reviews the working diff itself for signs of over-building — a newly-added function with a single call site, a thin forwarding wrapper, a new dependency with a stdlib equivalent, a possible duplicate helper. It is advisory only and never blocks a write; silence is not proof the change is minimal. Its single-use-abstraction finding in particular is capped at Low confidence today, because the call graph behind it is intra-file — a symbol it calls single-use can still have callers in another file. Confirm a Low-confidence single-use finding with find_references before acting on it; do not inline a symbol on this finding alone.
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.
- 7d ago First seen · 45 lines · 22 tokens per session scan A 31452bc6e2f9
plumb-minimal-change is a skill published in the GitHub repository plumbkit/plumb (4 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 590 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
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…
design-review
Deep design review of Go codebase — naming, structure, consistency, interfaces, error handling. Scores each dimension and provides actionable fixes.
vhs-e2e-gif
Record a test run, a TUI session, or any terminal command as a GIF with VHS and attach it to a GitHub PR as a release-hosted asset, never a repo commit. Use when asked to record an e2e run, demo a fix on a PR, attach a GIF or screen recording to a pull request, show a test passing visually, or produce a terminal…
agents-md
Generate AGENTS.md files for Go, Rust, TypeScript, and Java projects. Use this skill whenever the user asks to create, scaffold, bootstrap, update, or review an AGENTS.md (or agent-instructions, CLAUDE.md, repo guide for agents) file in a codebase. Also trigger when the user says "add AGENTS.md", "make this repo…
code-review-pi
Review code for quality, run linters, check test coverage, fix issues, and enforce gates. Save the final report to ./specs/issues/003-code-review-pi/PROMPT.md. Use before committing changes.
pi-go-review
Review ported Go code for idiomatic quality — that the port maximizes Go rather than transliterating TypeScript. Use after porting upstream pi changes, or standalone on any diff in this repo.