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 sprngr/rubber-duck --skill duck-tidygit clone --depth 1 https://github.com/sprngr/rubber-duckWrote 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/sprngr/rubber-duck/duck-tidy)<a href="https://agentmods.dev/skills/sprngr/rubber-duck/duck-tidy"><img src="https://agentmods.dev/badge/skills/sprngr/rubber-duck/duck-tidy/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/sprngr/rubber-duck/duck-tidy"><img src="https://agentmods.dev/badge/skills/sprngr/rubber-duck/duck-tidy.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 | $0.00065 | $0.02435 |
| Opus 5 | $0.00032 | $0.01218 |
| Sonnet 5 | $0.00013 | $0.00487 |
| Haiku 4.5 | $0.00006 | $0.00244 |
Grade A, and why
duck-tidy 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 11d 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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stale comment and doc cleanup 🦆🧹. Audit-first, evidence-backed staleness detection.
Purpose
Identify stale/outdated comments and non-CONTEXT docs so they stop polluting future sessions and confusing agents and developers. Audit-first; edits hand off to duck-patch.
Philosophy Guardrails (skill-local)
Inherit shared guardrails from references/GUARDRAILS.md.
- ask 1-3 targeted clarifying questions when context is incomplete
- state assumptions explicitly when evidence is missing
Skill-specific delta:
- Staleness evidence-backed: comment contradicts current code, describes behavior no longer existing, or documents worktree-only add/remove never merged to main.
- TODO/FIXME/HACK/XXX markers out of scope (duck-debt owns the ledger).
- ADR/design notes historic by design: if info is superseded, flag it; do not edit.
Activation
Audit-only (default): scan, report, no edits. Signals: "duck-tidy", "stale comments audit", "outdated docs audit".
Audit-and-edit: audit, then hand agreed findings to duck-patch. Signals: "tidy and fix comments", "clean up stale comments".
Method
1. Scan scope
Scope: explicit paths/globs from user, else worktree files (tracked + untracked, git-ignored excluded) minus CONTEXT.md, .duck-tape/, and common generated dirs (build/, dist/, node_modules/, coverage/, target/).
If the repo's generated dirs differ, ask one question before scanning.
If scope unclear, ask one question: single file / directory / worktree diff vs default branch.
Collect code comments, doc comments, non-CONTEXT markdown in scope.
2. Gather staleness evidence
Stale iff any rule holds:
- Contradiction: text contradicts current code (outdated invariants, wrong parameter semantics, old return type or signature).
- Removed behavior: describes functionality no longer present (referenced symbol/function/feature deleted).
- Worktree-only add/remove: documents behavior added then removed in the
current worktree, never merged to the default branch. Verify via
git diff <default-branch>: behavior exists only in unmerged worktree changes. Resolve default branch withgit symbolic-ref refs/remotes/origin/HEAD, fall back tomain. For untracked files, confirm worktree-only status viagit status --porcelain.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 223 lines · 65 tokens per session scan A 8bf19295d342
duck-tidy is a skill published in the GitHub repository sprngr/rubber-duck (8 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 2,435 once invoked, about $0.0003 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
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
security-review
Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…
review
Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.
reply-to-pr-threads
Draft, confirm, and post replies to GitHub PR review threads. Handles per-category reply formatting, re-fetches thread resolution state so auto-resolved threads are skipped, and posts via GraphQL. Use when the user asks to "reply to PR threads", "post PR thread replies", or "draft PR reply messages".