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/fall-out-bug/sdp/featurenpx skills add fall-out-bug/sdp --skill featuregit clone --depth 1 https://github.com/fall-out-bug/sdpWhat 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 | $0.00020 | $0.01961 |
| Opus 5 | $0.00010 | $0.00981 |
| Sonnet 5 | $0.00004 | $0.00392 |
| Haiku 4.5 | $0.00002 | $0.00196 |
Grade A, and why
feature 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 2d 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@feature
Orchestrate product discovery, requirements, UX research, and workstream design.
Phase 0: This skill targets Go projects (e.g. go build/go test in acceptance criteria). Language-agnostic expansion is planned.
Three Explicit Modes (No Auto-Detection)
Key Principle: User must explicitly choose the mode. No hidden context detection. Same input + same mode = identical output.
| Mode | When to use | Steps | Questions |
|---|---|---|---|
--default (or no flag) |
New/exploratory feature. Full interactive discovery. | 0, 1, 2, 2.5, 3, 3.5, 4 | Interactive (3-5 questions) |
--quick |
User knows what they want, just needs workstreams. | 3 only | 0 questions - goes directly to @design |
--auto |
Feature already described in roadmap/plan. Non-interactive. | 0, 3, 4 only | 0 questions - reads from docs/ROADMAP.md |
Mode Behavior Guarantee
Deterministic: Each mode produces identical behavior given identical input. No context sniffing, no heuristics, no "smart defaults."
--default: Always asks the same questions in the same order--quick: Always skips to @design with zero questions--auto: Always reads from roadmap/plan docs, never asks questions
--auto Mode (Recommended for Roadmap Features)
For features already defined in docs/ROADMAP.md:
Step A: Extract from Roadmap (Non-Interactive)
- Find the feature in the roadmap:
rg "F0\d\d" docs/ROADMAP.md -A 10 - Extract: feature ID, description, success criteria, listed deliverables
- Identify scope: what files/packages this touches (from deliverables and codebase)
No questions asked. Read from docs only.
Step B: Auto-Generate Workstreams
For each deliverable, create workstream files using this format:
---
ws_id: 00-FFF-SS
feature_id: FFFF
status: open
priority: P1
size: M
depends_on: []
ws_kind: leaf|aggregate
parent_ws_id: null|00-FFF-SS
dispatch_lifecycle: active
---
# 00-FFF-SS: Feature Name — Step Description
## Goal
One paragraph: what this workstream does and why.
## Scope Files
- path/to/file/or/dir (exact files or directory prefixes)
- ...
## Beads
- primary: sdplab-XXXX # leaf only
- finding: sdplab-YYYY # optional
## Acceptance Criteria
- [ ] Specific, testable criterion 1
- [ ] Specific, testable criterion 2
- [ ] go build ./... passes
- [ ] go test ./... passes
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.
- 2d ago First seen · 198 lines · 20 tokens per session scan A 84591b71c700
feature is a skill published in the GitHub repository fall-out-bug/sdp (19 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 1,961 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 2026-08-30.
Other skills, from other repositories
ui-design
Use when users need visual direction, interface hierarchy, layout decisions, design specifications, or prototypes before implementing a Web or mini program UI.
panel-review-loop
Iteratively review and improve a Fallow user-facing surface across representative real-world projects until the panel has no blocking concerns.
hyperframes-animation
All animation knowledge for HyperFrames — atomic motion rules, multi-phase scene blueprints, scene transitions, broader motion-design techniques, AND the seven runtime adapters (GSAP default, plus Lottie, Three.js, Anime.js, CSS keyframes, Web Animations API, TypeGPU). Use for any motion or animation task: pick 2-4…
ui-designer/interaction-specification
交互规范，定义加载状态、空状态、反馈机制、动效、无障碍等交互细节.
ui-designer/design-system
设计系统规范，包含颜色、字体、间距、圆角、阴影、动效等基础设计token.
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.