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-adaptgit 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-adapt)<a href="https://agentmods.dev/skills/sprngr/rubber-duck/duck-adapt"><img src="https://agentmods.dev/badge/skills/sprngr/rubber-duck/duck-adapt/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-adapt"><img src="https://agentmods.dev/badge/skills/sprngr/rubber-duck/duck-adapt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 188 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00047 | $0.02147 |
| Opus 5 | $0.00023 | $0.01073 |
| Sonnet 5 | $0.00009 | $0.00429 |
| Haiku 4.5 | $0.00005 | $0.00215 |
Grade A, and why
duck-adapt 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 10d 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 — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill adapter 🦆. External skill -> duck philosophy.
Purpose
Transform external skills or workflows into rubber-duck-grounded versions that preserve intent while adding:
- Socratic questioning flow
- Evidence-first discipline
- Duck Ladder minimal-change thinking
- Execution approval gates
- Prompt order standard compliance
Also validates existing duck-* skills and detects unnecessary duplication.
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:
- Meta-skill: operates on skill definitions, not codebase directly
- Output is skill draft, not implementation
- Recommends skill rejection when overlap/duplication detected
Activation
Use when:
- User provides external skill to adapt
- User describes workflow/process to convert into skill
- User asks to audit existing skill for philosophy compliance
- User asks "should we add this skill" or "does this overlap"
Method
1. Intake and classification
Ask clarifying questions (up to 3) to establish:
For external skill adaptation:
- Input format: full skill markdown, workflow doc, or concept description?
- Intent: what problem does this skill solve?
- Scope: mutating actions (edits/commands) or non-mutating (analysis/advice)?
- Target audience: what context does user expect?
For skill audit:
- Which skill to audit? (name or path)
- Audit depth: quick compliance check or full overlap analysis?
For overlap detection:
- Skill concept summary
- Expected workflow steps
- Comparison against existing skills requested?
2. Evidence gathering
For external skill:
- Parse input: extract steps, constraints, outputs, examples
- Identify decision points (where user choice matters)
- Identify mutating actions (require approval gates)
- Identify evidence gaps (where code/diff/log reading needed)
For skill audit:
What ships with it
7 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.
- 10d ago First seen · 307 lines · 47 tokens per session scan A ad78916dfd82
duck-adapt is a skill published in the GitHub repository sprngr/rubber-duck (8 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 2,147 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
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.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
taiyi-ui-design
A design-planning guide for describing how an application's user interface should look and behave. It produces a UI-DESIGN.md document covering layouts, components, interactions, accessibility, and error states.
ln-62-repository-publisher
Commits, pushes, and remotely verifies authorized repository changes. Not for releases, package publication, or announcements.
remove
Remove a deployed framework or addon from the current workspace.
maggy
Maggy is a local AI engineering command center. AI-prioritized inbox across issue trackers (GitHub Issues/Asana), one-click TDD execute with iCPG context enrichment, daily competitor intelligence briefing.