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-simplifygit 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-simplify)<a href="https://agentmods.dev/skills/sprngr/rubber-duck/duck-simplify"><img src="https://agentmods.dev/badge/skills/sprngr/rubber-duck/duck-simplify/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-simplify"><img src="https://agentmods.dev/badge/skills/sprngr/rubber-duck/duck-simplify.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 | $0.00042 | $0.00767 |
| Opus 5 | $0.00021 | $0.00383 |
| Sonnet 5 | $0.00008 | $0.00153 |
| Haiku 4.5 | $0.00004 | $0.00077 |
Grade A, and why
duck-simplify 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 9d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Simplify 🦆. Smaller shape, same behavior. Prevent divergence, not just repetition.
Purpose
Find highest-value simplifications without weakening security, correctness, or explicit requirements.
Philosophy Guardrails (skill-local)
Inherit shared guardrails from references/GUARDRAILS.md.
Skill-specific delta:
- Complexity-reduction guidance only; final implementation decisions remain with user.
Activation
Use for complexity-minimization lens in review/design/debug contexts, including semantic duplication/divergence review.
Method
1. Clarify scope (if unclear)
- ask 1-3 targeted clarifying questions when context is incomplete
- state assumptions explicitly when evidence is missing
Required:
- code/proposal scope
Dry-mode required:
- two or more candidate scopes with suspected semantic duplication
Optional:
- constraints (deadline, readability norms, team preference)
If constraints unclear, ask one targeted clarifying question.
2. Review for simplification
- Identify complexity hotspots (layers, branches, config surface, indirection).
- Verify evidence (callers, branch count, config usage) before recommendation.
- Emit max 3 highest-impact simplifications.
- Prefer deletion/reuse/stdlib/native before new abstraction.
- For DRY-mode: confirm semantic duplication (not syntax-only), include
Diverges when+Extract start, and prefer smallest safe extraction boundary. - If simplification would weaken trust boundaries/accessibility/explicit requirements, refuse and suggest safe alternative.
- Do not flag tiny repetition that improves readability or low-risk literals/constants.
3. Output findings
Standard mode:
One line per finding:
<prefix> <path[:line|scope]> — <complexity cost>. Fix: <smaller shape>.
Prefixes:
🪶 yagni:abstraction/config not justified yet📚 stdlib:custom code replaceable by standard library🧱 native:dependency/custom layer replaceable by platform feature✂️ shrink:same behavior in fewer lines🗑️ delete:dead/speculative code removable with no replacement❓ question:missing intent blocks judgment
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.
- 9d ago First seen · 107 lines · 42 tokens per session scan A 9d6f834c9ae0
duck-simplify is a skill published in the GitHub repository sprngr/rubber-duck (8 stars, last pushed 4d ago), licensed MIT. It adds 42 tokens to every session and 767 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
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".