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 commands/aziontech/webkit/regen-baselinesgit clone --depth 1 https://github.com/aziontech/webkitWhat 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 | $0.00000 | $0.00463 |
| Opus 5 | $0.00000 | $0.00231 |
| Sonnet 5 | $0.00000 | $0.00093 |
| Haiku 4.5 | $0.00000 | $0.00046 |
Grade A, and why
regen-baselines 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 yesterday.
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
/regen-baselines <branch | pr-number | pr-url> [modes]
Regenerate the Linux visual baselines for a PR branch in CI and land them on the
branch. Never generate baselines locally — macOS rendering does not match the linux/
snapshots the PR visual gate (governance.yml → test:visual:ci) compares against.
Run the regen-baselines skill (.claude/skills/regen-baselines/SKILL.md). It:
- Resolves the branch (from the PR number/URL when given) and confirms the state to
snapshot — e.g. the
mainmerge/rebase — is already pushed to origin. - Triggers
Storybook Regenerate Baseline(.github/workflows/app-storybook-generate-baseline.yml) withupdate_baselines=true, optionally narrowing to amodessubset. - Waits for the run (~5 min with warm caches) and downloads the
visual-baselines-linuxartifact into a fresh temp dir. - Mirrors it into
apps/storybook/.storybook/test-visual/__image_snapshots__/linux/withrsync -a --delete, so deletions of stale snapshots propagate. - Reviews the diff scope — every changed story must be explainable by the branch's changes; unexplained stories stop the flow.
- Commits only the snapshots folder (
test(storybook): regenerate linux baselines …) and pushes, updating the PR.
modes is a comma-separated subset of the matrix in
apps/storybook/.storybook/visual-modes.js (e.g. light-desktop,dark-mobile);
empty = the full {dark,light} × {desktop,tablet,mobile} cross product. The
dark-desktop snapshot is the historical unsuffixed <story>.png.
Conflict recovery: when main and the branch both regenerated the same snapshots,
finish the merge/rebase first (any side of a conflicted PNG is fine — it is about to be
overwritten), push, then run this flow so the committed baselines come from the merged
tree.
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.
- yesterday First seen · 32 lines · 0 tokens per session scan A 8b464351abca
regen-baselines is a command published in the GitHub repository aziontech/webkit (2 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 463 tokens. 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 2026-08-31.
Other commands, from other repositories
speckit.tasks
Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.
diagnose
Run sivtr doctor to check the environment, then investigate any failing checks.
test-changed
Run the full quality gate on only the files changed since branching from main.
route
Route notes from inbox to appropriate vault destinations.
cleanup-transcript
Clean up a video/audio transcript (SRT or plaintext) - identifies structure, fixes transcription errors, asks clarifying questions iteratively.
reflect
Capture learnings from the current conversation through guided reflection.