Borrowing it
Nothing to install: this file belongs to cdavid817/vanehub-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cdavid817/vanehub-ai/main/.codex/skills/spec-optimizer/SKILL.mdgit clone --depth 1 https://github.com/cdavid817/vanehub-aiWrote 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/cdavid817/vanehub-ai/spec-optimizer)<a href="https://agentmods.dev/skills/cdavid817/vanehub-ai/spec-optimizer"><img src="https://agentmods.dev/badge/skills/cdavid817/vanehub-ai/spec-optimizer/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/cdavid817/vanehub-ai/spec-optimizer"><img src="https://agentmods.dev/badge/skills/cdavid817/vanehub-ai/spec-optimizer.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 | $0.00051 | $0.00288 |
| Opus 5.5 | $0.00020 | $0.00115 |
| Sonnet 5.5 | $0.00010 | $0.00058 |
| Haiku 4.5 | $0.00005 | $0.00029 |
Grade A, and why
spec-optimizer 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.
What it actually says
Spec Optimizer
Analyze openspec/specs/ only. Never edit openspec/specs/ or openspec/changes/archive/ during analysis.
- Parse capability, Requirement, Scenario,
SHALL, andMUSTunits. - Report duplicate candidates and capability clusters as recommendations, not facts.
- Flag specs above 500 lines or 8,000 tokens unless the user supplies different budgets.
- For every proposed merge, create a mapping from each source Requirement and Scenario to a retained target or an explicit rejection reason.
- Fail the coverage check when any source
SHALLorMUSTis missing from the mapping. - Write review artifacts in a new OpenSpec change:
analysis/report.md,analysis/mapping.md,analysis/coverage.md,analysis/diff.md, and proposed delta specs. - Stop before applying changes. Ask the user to review the artifacts and use the normal OpenSpec workflow for approved edits.
Use the archive catalog only to locate historical context after a main-spec candidate is identified; do not optimize or rewrite archive artifacts.
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 · 19 lines · 51 tokens per session scan A a4d3c6a0aebf
spec-optimizer is a skill published in the GitHub repository cdavid817/vanehub-ai (109 stars, last pushed 4d ago), licensed Apache-2.0. It adds 51 tokens to every session and 288 once invoked, about $0.0002 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
install-iterm-agent-fork
Install and set up pirate/iterm-agent-fork locally for iTerm2 agent-session forking. Use when a user asks to install, configure, repair, update, or verify the iTerm Agent Fork repo, AutoLaunch script, iTerm Python API launch, Cmd+Shift+F/Cmd+Shift+G key bindings, or optional casr cross-agent handoff support.
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
cdf-anomalygen
Use when running the CDF AnomalyGen pipeline over a defect dataset — mask placement, fine-tuning, synthetic defect-image generation (SDG), evaluation, quality refinement, and pseudo-labeling — even when the user names only one stage.
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
holoscan-install-wheel
Install Holoscan SDK 5.x CUDA 13 Python wheels in an isolated environment, choosing the full stack or version-matched components.