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 OutlineDriven/outline-driven-development --skill frame-rate-stabilitygit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outlinedriven/outline-driven-development/frame-rate-stability)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/frame-rate-stability"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/frame-rate-stability/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/outlinedriven/outline-driven-development/frame-rate-stability"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/frame-rate-stability.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 | $0.00055 | $0.00894 |
| Opus 5 | $0.00028 | $0.00447 |
| Sonnet 5 | $0.00011 | $0.00179 |
| Haiku 4.5 | $0.00006 | $0.00089 |
Grade A, and why
frame-rate-stability 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frame-rate stability
Contract
| Field | Bound contract |
|---|---|
| Trigger | A rendering path needs stable multi-metric performance against fixed targets. |
| Authority | Reversible local: write only named local artifacts; state and follow the rollback path before mutating. |
| Side effect | Multi-metric frame-rate stabilization: local writes to the rendering path and its configuration. |
| Done | Every fixed target holds for two consecutive comparable runs. |
| Stop | Stalled; blocked; capped. Bound: fixed hardware, build, scene, settings, budget, and target values. |
Inputs
- Fixed hardware, build, scene, settings, and budget (required): all parameters that affect rendering performance, named and frozen before any mutation.
- Target values (required): fixed numeric thresholds for each metric: frame-time (ms or FPS), CPU (ms or %), GPU (ms or %), and memory (MB or GB). Every target must be a concrete number, not a directional goal like "lower" or "faster".
Procedure
- Bind the fixed hardware, build, scene, settings, budget, and target values. Freeze all before any mutation. Done when: every bound element is named and frozen, including a concrete numeric target for each metric.
- Stabilize the configuration against the fixed targets. Adjust rendering-path settings (quality levels, resolution scaling, draw-call batching, shader complexity, asset streaming) to meet every target. Collect frame-time, CPU, GPU, and memory evidence per change. Done when: every target is addressed with evidence showing the current configuration meets or misses it.
- Define the sampling window and run-comparability rules. The sampling window is the fixed duration or frame count over which metrics are measured (for example, 10 seconds or 600 frames at a fixed scene position). Run-comparability requires: same hardware, same build, same scene, same settings, same sampling window, same measurement tool. Declare the window and rules before running. Done when: the sampling window and comparability rules are declared in writing.
- Execute two consecutive comparable runs. Both runs use the frozen inputs, the declared sampling window, and the same measurement tool. Record per-target results for each run. A target holds only if both runs meet its threshold. If a target fails in either run, revisit step 2. Done when: both runs complete with per-target results recorded, or a target fails and is revisited.
- Stop at success (all targets hold for two consecutive comparable runs), any non-success terminal, or the bound. Done when: a terminal class is reached and named.
- Persist the run record to
.outline/loops/frame-rate-stability/<run_id>/when durable. Emitreceipt.jsonbefore return. Done when: the receipt is written with per-target evidence from both runs, the sampling window, and the terminal class.
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.
- 5d ago First seen · 43 lines · 55 tokens per session scan A f6cc4b5f48b8
frame-rate-stability is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 4d ago), licensed Apache-2.0. It adds 55 tokens to every session and 894 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 2026-09-03.
Other skills, from other repositories
frame-rate-stability
Use when a rendering path needs stable frame-time, CPU, GPU, and memory evidence against fixed targets. Not for one-shot profiling or visual quality review.
unity-manual-component
Manually add, configure, reorder, and copy components on GameObjects using Unity Editor UI. For one-off Inspector workflows that do not need REST automation.
systematic-param-sweep
A method for tuning several parameters one at a time while observing and recording their individual effects. It uses large changes to discover an effect and smaller changes to refine it.
muzzle-flash
Use when authoring a muzzle-flash visual effect — a one-shot 80 ms burst at a gun barrel built with a particle one-shot OR a flashing quad with a star-burst shader. Trigger on "muzzle flash", "gun fire", "weapon flash", "barrel flash", "shoot a gun", "spell-cast burst at hand".
organic-model
Use when generating organic shapes — trees, rocks, mushrooms, coral, bushes, alien plants, vines, crystals, fruit, bones. The "easy mode" of 3D generation; AI artifacts read as natural irregularity. Trigger on "make a tree", "generate rocks", "I need foliage", "mushroom prop", "alien plants", "fill the scene with…
hz-unity-passthrough-camera-access
Meta Quest Passthrough Camera Access (PCA) for Unity — access the forward-facing RGB cameras on Quest 3 / Quest 3S to feed Computer Vision and Machine Learning pipelines. Use when capturing the passthrough camera image/texture, reading the camera pose and intrinsics, projecting camera pixels into world space via…