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/sprngr/rubber-duck/duck-patchnpx skills add sprngr/rubber-duck --skill duck-patchgit 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-patch)<a href="https://agentmods.dev/skills/sprngr/rubber-duck/duck-patch"><img src="https://agentmods.dev/badge/skills/sprngr/rubber-duck/duck-patch.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 | $0.00042 | $0.02028 |
| Opus 5 | $0.00021 | $0.01014 |
| Sonnet 5 | $0.00008 | $0.00406 |
| Haiku 4.5 | $0.00004 | $0.00203 |
Grade A, and why
duck-patch 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 5d 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Patch execution 🦆. Smallest safe diff first.
Purpose
Execute a narrowly scoped code change once the fix direction is known.
Philosophy Guardrails (skill-local)
Inherit shared guardrails from references/GUARDRAILS.md.
Skill-specific delta:
- Executes bounded implementation only; product and architecture decisions remain with user.
Activation
Use when user asks for a targeted code edit and scope is clear (or can be clarified quickly).
Method
Subagent execution mode
When running as a subagent without a user channel (e.g., via duckling): do not apply edits or run commands. Execute scope clarification, Duck Ladder, and patch derivation as analysis; replace "apply minimal safe diff" and "run smallest agreed check" with approval-package content: the derived per-file diff blocks and verification plan. Emit per the host wrapper's contract (preflight + diffs + approval ask + status footer).
1. Clarify scope (if incomplete)
- ask 1-3 targeted clarifying questions when context is incomplete
- state assumptions explicitly when evidence is missing
Mutating action gate: Workspace-changing actions (require approval based on change type):
Semantic changes (require full execution approval):
- Code/logic changes
- Documentation/planning changes (README, markdown docs, ADRs, CONTEXT.md, runbooks, design notes), except typo-only fixes in non-code text files
- Config/schema changes (settings, env vars, build config)
- Dependency changes (package.json, requirements.txt, etc.)
- File operations (create, delete, move)
- Mutating commands (git commit, install, build, deploy)
- Task delegation for implementation/patching
Cosmetic changes (require lightweight confirmation):
- Formatting/whitespace-only changes
- Typo fixes in non-code text files
- Confirmation phrase: "Confirm to proceed with [formatting change/typo fix]?"
Edge cases:
- JSDoc/docstring changes in code files are semantic (affects generated docs, code contracts)
- Comments explaining logic in code are semantic (affects maintainability understanding)
- Config comments are semantic (affects interpretation)
- Document updates (ADRs, CONTEXT.md) are semantic
- Examples in README that are code snippets are semantic (users copy-paste)
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.
- 5d ago First seen · 183 lines · 42 tokens per session scan A 283f22419be7
duck-patch is a skill published in the GitHub repository sprngr/rubber-duck (8 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 2,028 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
decision-challenge
Use when a high-impact plan, migration or architecture claim needs a bounded adversarial challenge before commitment. Isolates claims from persuasion, attacks assumptions, reconciles doubts with evidence and emits proceed/hold/stop. NOT a finished-diff review (review/code-review), NOT SDD artifact consistency…
Logic Torturing 論理検証
変更に含まれる設計判断・実装選択の論理的整合性を徹底的に検証し、確証バイアスを排除して判断精度を高める.
apply-constructive-dissent
Use when building or assessing a team, decision process, or organizational culture where you need genuine diverse thinking to surface before commitment — not after — and where the risk is false consensus rather than open conflict.
adversary
Forces the model to build a genuine prosecution case against its own answer before delivering it.
expert-redteam-review
Use when a user asks to evaluate a complex, high-impact, ambiguous, cross-functional, or hard-to-reverse decision; mentions expert panel, red team, adversarial review, rebuttal, judge, arbitration, risk review, challenge assumptions, poke holes, or wants stronger decision quality than a normal review.
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.