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-reviewgit 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-review)<a href="https://agentmods.dev/skills/sprngr/rubber-duck/duck-review"><img src="https://agentmods.dev/badge/skills/sprngr/rubber-duck/duck-review/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-review"><img src="https://agentmods.dev/badge/skills/sprngr/rubber-duck/duck-review.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 | $0.00029 | $0.01084 |
| Opus 5 | $0.00015 | $0.00542 |
| Sonnet 5 | $0.00006 | $0.00217 |
| Haiku 4.5 | $0.00003 | $0.00108 |
Grade A, and why
duck-review 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review 🦆. Keep terse, actionable format by default.
Purpose
Review changed code with risk-first, actionable findings in paste-ready format.
Philosophy Guardrails (skill-local)
Inherit shared guardrails from references/GUARDRAILS.md.
Skill-specific delta:
- Provide findings and fix directions; user decides merge/approval outcomes.
Activation
Use when user asks to review diff/code/PR for issues and fix direction.
Method
1. Clarify context (if ambiguous)
-
ask 1-3 targeted clarifying questions when context is incomplete
-
state assumptions explicitly when evidence is missing
-
If review context is ambiguous, ask one targeted clarifying question first.
-
Anchor each finding in explicit diff/code evidence.
2. Apply Duck Ladder (complexity guard)
When proposing fix direction, stop at first rung:
- No change needed (YAGNI)
- Reuse existing local helper/pattern
- Replace with stdlib/native
- Use already-installed dependency
- Shrink to smallest safe diff
- Only then add new code/abstraction
3. Review workflow
- Confirm review input exists (diff, PR text, or pasted code chunk). If missing, ask for concrete review target.
- Scan in priority order: security -> correctness -> data integrity -> performance -> tests -> docs -> simplification.
- Emit only actionable findings. One line each: location, problem, fix direction.
- Use strongest matching prefix. If multiple apply, pick highest risk prefix.
- Enforce strict output shape: one-line prefixed comment template for every finding.
- For security or irreversible-risk findings, switch to full paragraph (Auto-Clarity), then resume terse comments.
- Huge refactor: report highest-impact findings first; avoid line-noise nits.
- Uncertain finding: ask one clarifying question instead of inventing certainty.
- Same line has multiple problems: split into separate comments when fixes differ.
If prefix choice unclear or reviewer needs wording examples, load references/review-comment-examples.md.
What ships with it
2 files 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 · 116 lines · 29 tokens per session scan A 15b1525628fe
duck-review is a skill published in the GitHub repository sprngr/rubber-duck (8 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 1,084 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
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".