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 ambient-code/platform --skill workflowgit clone --depth 1 https://github.com/ambient-code/platformWrote 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/ambient-code/platform/workflow)<a href="https://agentmods.dev/skills/ambient-code/platform/workflow"><img src="https://agentmods.dev/badge/skills/ambient-code/platform/workflow/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/ambient-code/platform/workflow"><img src="https://agentmods.dev/badge/skills/ambient-code/platform/workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00016 | $0.03526 |
| Opus 5.5 | $0.00006 | $0.01410 |
| Sonnet 5.5 | $0.00003 | $0.00705 |
| Haiku 4.5 | $0.00002 | $0.00353 |
Grade A, and why
workflow 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 1mo 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ambient UI Development workflow
Strict workflow execution to be used when performing any ambient-ui component work.
User Input
$ARGUMENTS
Workflow
1. Align with Specs
All work must be aligned with specs. If the user or instructions are asking for work to be done without a verified matching section in a spec, STOP.
Before proceeding with implementation, update the relevant spec to match the request.
2. Perform Test Driven Development
Determine the size of the work. If it is large, break it down into smaller atomic units of work and execute this workflow for each one. You can use subagents to handle this gracefully, preserving your context.
Define tests that are relevant and that, when they pass, provide a genuine trust that the system is properly implemented in a way that aligns with the spec and the user's intent.
Then, proceed with methodical implementation, breaking work into atomic units of work for subagents when possible. Bias towards using subagents for implementation tasks, but ensure they read this workflow skill to understand the development standards.
Test and verify implementation before proceeding to the next step.
Standards
These standards are to be used during all ambient-ui component development work.
Fakes over Mocks
When testing, fakes are to be preferred over mocks. Tests that don't test reality are not tests at all.
Accessibility
-
For Red Hat assets, small text (17pt or smaller) needs to have a 4.5:1 contrast ratio at minimum. Large text (18pt or larger) and informative graphics like icons need to have a 3:1 contrast ratio at minimum.
-
Saturated hues that are similar in intensity can vibrate when used together, creating fuzziness around the edges like a glowing blur. These colors can be difficult for anyone to look at and distinguish, and even painful for those with vision differences. An example of high-contrast colors that do not vibrate.
Do this: Combine bright colors with less saturated and neutral colors. Image showing misuse: An example of low-contrast colors that vibrate.
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.
- 1mo ago First seen · 264 lines · 16 tokens per session scan A 0e65a3087871
workflow is a skill published in the GitHub repository ambient-code/platform (131 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 3,526 once invoked, about $0.0001 per session on Opus 5.5. 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
08-debug
Reproduce and fix a known bug, or find an unknown root cause by hypothesis validation. Use when the user wants to fix a bug, find why something breaks, or reopen a stuck investigation. Not for building a feature or reviewing a diff.
chimera-write-the-check-before-the-code
A criterion written after the implementation describes the implementation. Write the failing check first, watch it fail, then build.
Learn what defines effective BDD scenarios
Interactive guidance on writing complete, effective BDD scenarios for story-flow.
hatch3r-bug-fix
Step-by-step bug fix workflow. Diagnose root cause, implement minimal fix, write regression test. Use when fixing bugs, working on bug report issues, or when the user mentions a bug.
ap-policies
Attach a completion policy gate (shell check or judge-agent rubric) to a session or fan-in group so turn-end only passes when the gate is green, then optionally auto-commit pending human ack. Use when the user says "gate this session on tests passing", "attach a policy", "commit only if tests are green", "judge…
systematic-debugging
Structured root-cause debugging loop — reproduce, isolate, form a hypothesis, verify the fix. Use whenever a bug, crash, test failure, or unexpected behavior is reported.