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/partikularwaters/banka/watershednpx skills add partikularwaters/Banka --skill watershedgit clone --depth 1 https://github.com/partikularwaters/BankaWrote 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/partikularwaters/banka/watershed)<a href="https://agentmods.dev/skills/partikularwaters/banka/watershed"><img src="https://agentmods.dev/badge/skills/partikularwaters/banka/watershed.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 | $0.00051 | $0.02189 |
| Opus 5 | $0.00026 | $0.01094 |
| Sonnet 5 | $0.00010 | $0.00438 |
| Haiku 4.5 | $0.00005 | $0.00219 |
Grade A, and why
watershed 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A single reviewer, however careful, has one perspective. Some decisions are worth more than that — not because the reviewer is bad at reviewing, but because different failure modes are visible from different angles, and a security-minded read misses what a maintainability-minded read catches, and neither catches what a real end-user's experience would.
This skill does not replace survey (which checks against this project's own declared rules) or dredge (which diagnoses a specific known failure). It's for the case where the question is genuinely open — a plan not yet committed to, a piece of code with no obvious single "correct" answer, an architectural fork where reasonable engineers would land in different places.
Context Contract
Required: the explicitly supplied subject (code, plan, or idea) — or, if
none was given, the most recent relevant work in this session · the resolved
tier's declared files (Standard: /context/; Core: /core/; Minimal: the
Banka-owned AGENTS.md block).
Conditional: a subagent/parallel-dispatch tool, when available, to run the five perspectives concurrently rather than sequentially in-session.
Excluded by default: project-specific invariants this skill would have to invent for an unstructured, non-Banka repository — it states that no Banka state was found instead.
Outputs: a consolidated audit (per-perspective findings, points of agreement, named tensions, one prioritized recommendation) — never five unresolved opinions handed to the user to referee.
Write authority: none. The audit is presented and the skill stops; it never implements its own recommendation.
Step 0 — Confirm what's being audited and why
Before running anything, be clear with the user: is this code, a plan/proposal, or an idea/direction? And what's the actual decision at stake — what would change depending on what this audit finds? An audit with no clear stake behind it just produces five opinions with nowhere to land.
Step 1 — Read what's needed
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 · 146 lines · 51 tokens per session scan A 9a8cceb89bcb
watershed is a skill published in the GitHub repository partikularwaters/Banka (3 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 2,189 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
tastemaker
Generate genuinely beautiful, on-brand UI instead of generic "AI slop" — use whenever the user asks to build, design, style, or improve a UI, landing page, dashboard, app screen, or component, whenever a PRD/spec needs a design pass before implementation, whenever the user pastes reference images/Pinterest/Dribbble…
fde
Keeps the engagement record for client work. Use when they name a client or stakeholder. Use when they debrief a meeting or paste notes. Use when they ask what was agreed. Use when they run a POC, change the client's codebase, prove it on their staging, go live, or need evals before a model acts. Use when they prep a…
kubernetes-skill
Prevent Kubernetes hallucinations by diagnosing and fixing failure modes: insecure workload defaults, resource starvation, network exposure, privilege sprawl, fragile rollouts, and API drift. Use when generating, reviewing, refactoring, or migrating manifests, Helm charts, Kustomize overlays, cluster policies, and…
image-to-psd
将一张或多张图片转换为经过严格质量校验的分层 PSD；可独立运行，也可使用 image2editable 的 Host、Local 或本地服务 Agent。输出修复背景、独立透明视觉组件和可编辑 Photoshop 文字图层。仅支持图片输入，不用于 PDF 或 PPTX。.
img2mo-learn
Learn reusable 2D motion-generation knowledge from user-specified action resources with /img2mo-learn . Use when the user provides videos, extracted frame sequences, spritesheets, Spine assets, generated outputs, failed attempts, or reference motion folders and wants to summarize animation timing, pose beats, style…
img2mo-std
Standardize a 2D animation baseline image with /img2mo-std xxx.png/pos. Use when preparing a character, creature, prop, or weapon baseline before motion generation, especially if the source image is too large, tightly cropped, lacks transparent action margin, has a white background, or later walk/attack/idle frames…