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 nanparth/ai-skill-hub --skill build-deterministic-workflow-demosgit clone --depth 1 https://github.com/nanparth/ai-skill-hubWrote 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/nanparth/ai-skill-hub/build-deterministic-workflow-demos)<a href="https://agentmods.dev/skills/nanparth/ai-skill-hub/build-deterministic-workflow-demos"><img src="https://agentmods.dev/badge/skills/nanparth/ai-skill-hub/build-deterministic-workflow-demos/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/nanparth/ai-skill-hub/build-deterministic-workflow-demos"><img src="https://agentmods.dev/badge/skills/nanparth/ai-skill-hub/build-deterministic-workflow-demos.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 | $0.00152 | $0.01856 |
| Opus 5 | $0.00076 | $0.00928 |
| Sonnet 5 | $0.00030 | $0.00371 |
| Haiku 4.5 | $0.00015 | $0.00186 |
Grade A, and why
build-deterministic-workflow-demos 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build Deterministic Workflow Demos
Treat the demo as a causal, testable product simulation. Build evidence for what the audience sees, what caused each state change, and which exact source produced each artifact.
Route the request
Classify the work before editing:
| Request | Load |
|---|---|
| New story, content overhaul, or realism review | references/story-and-content.md, then references/workflow-and-gates.md |
| Screenshots and descriptions only | references/screenshot-intake.md, then references/story-and-content.md |
| Need visual examples of the contracts | references/example-evidence.md |
| Pacing, typing, agent output, or idle-gap repair | references/timing-and-readability.md |
| Click, Send, persistence, Timeline, diff, or scene-state repair | references/interaction-and-state.md |
| GIF colour, disposal, fade, clipping, or media integrity | references/rendering-and-colour.md, then references/evidence-and-release.md |
| Release, promotion, or cleanup | references/evidence-and-release.md |
| Independent source or artifact review | references/reviewer-roles.md, then the relevant gate reference |
| Recurring symptom or regression | references/anti-patterns.md |
| Simmis demo work | Load references/simmis-profile.md in addition to the relevant generic references |
Read references/workflow-and-gates.md for any end-to-end build.
Establish the evidence tier
Use the strongest available tier and label conclusions accurately:
- Source + runtime + media: prove causal interaction, geometry, timing, encoding, and release integrity.
- Rendered media + manifests: prove decoded visual behaviour and container properties, but not source causality unless manifests bind source hashes.
- Screenshots + descriptions: derive expected states, hierarchy, persistence, and visual defects. Mark unobserved behaviour as described or inferred; do not claim trusted input, timing, looping, or encoding integrity.
Never silently promote a visual-only inference into a product capability.
What ships with it
34 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.
- agents/openai.yaml 295 B
- assets/examples/bad/timeline-preselection-baseline.png 48 KB
- assets/examples/good/gif-fade-sequence.png 98 KB
- assets/examples/good/master-fade-sequence.png 156 KB
- assets/examples/good/reply-dwell.png 361 KB
- assets/examples/good/row-review-persistence.png 1140 KB
- assets/examples/good/send-ready-press-post.png 170 KB
- assets/examples/good/timeline-click-only.png 250 KB
- assets/examples/provenance.json 2.3 KB
- assets/templates/evidence-manifest.json 1.1 KB
- assets/templates/pacing-policy.yaml 819 B
- assets/templates/project-profile.yaml 1.2 KB
- assets/templates/review-report.md 2.4 KB
- assets/templates/scenario-brief.md 2.2 KB
- assets/templates/screenshot-index.yaml 1.6 KB
- assets/templates/story-bible.md 1.8 KB
- references/anti-patterns.md 10.0 KB
- references/evidence-and-release.md 11 KB
- references/example-evidence.md 3.4 KB
- references/interaction-and-state.md 8.8 KB
- references/rendering-and-colour.md 2.5 KB
- references/reviewer-roles.md 1.3 KB
- references/screenshot-intake.md 2.3 KB
- references/simmis-profile.md 10 KB
- references/story-and-content.md 2.7 KB
- references/timing-and-readability.md 7.4 KB
- references/workflow-and-gates.md 5.4 KB
- scripts/fingerprint_sources.py 3.7 KB runs code
- scripts/index_screenshots.py 2.6 KB runs code
- scripts/inventory_artifacts.py 4.6 KB runs code
- scripts/make_contact_sheet.py 2.9 KB runs code
- scripts/promote_artifacts.py 5.7 KB runs code
- scripts/scaffold_contract.py 1.7 KB runs code
- scripts/validate_timing_manifest.py 7.6 KB runs code
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 · 133 lines · 152 tokens per session scan A 6205dcd9f5c3
build-deterministic-workflow-demos is a skill published in the GitHub repository nanparth/ai-skill-hub (23 stars, last pushed 18d ago), licensed MIT. It adds 152 tokens to every session and 1,856 once invoked, about $0.0008 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
webgl-liquid-metal
A real-time liquid-metal shader — a domain-warped noise field shaded as molten chrome, with a sweeping specular highlight over an iridescent thin-film (cosine-palette) sheen. No textures. Rendered as a single self-contained index.html. Use when the brief asks for "liquid metal", "molten chrome", "iridescent"…
webgl-particle-galaxy
A real-time particle galaxy — tens of thousands of additive-blended GPU points spiraling around a bright core, their orbits solved entirely in the vertex shader (from glVertexID), so the whole cloud draws in one call. Rendered as a single self-contained index.html. Use when the brief asks for a "particle field"…
webgl-neon-grid
A real-time synthwave scene — a perspective floor grid scrolling toward a banded retro sun under a neon starfield, all from one fragment shader. No textures. Rendered as a single self-contained index.html. Use when the brief asks for "synthwave", "outrun", "retro 80s", "neon grid", "perspective grid", "vaporwave", or…
webgl-depth-gallery
A scroll-reactive 3D image gallery in Three.js: Z-stacked images crossfade over per-image mood backgrounds with velocity breath, a glowing cursor trail and an editorial CMYK/RGB/HEX/PMS color card.
webgl-horizontal-parallax
A horizontal-scroll WebGL gallery (Three.js): frames glide sideways with lerp smoothing and each image parallaxes its texture (UV shift) by its position in the viewport.
webgl-distortion-grain
A vertical gallery (Three.js) where planes bend with scroll velocity, ripple under the cursor via simplex noise, and carry a film grain.