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 tutur3u/platform --skill tuturuuu-web-releasegit clone --depth 1 https://github.com/tutur3u/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/tutur3u/platform/tuturuuu-web-release)<a href="https://agentmods.dev/skills/tutur3u/platform/tuturuuu-web-release"><img src="https://agentmods.dev/badge/skills/tutur3u/platform/tuturuuu-web-release/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/tutur3u/platform/tuturuuu-web-release"><img src="https://agentmods.dev/badge/skills/tutur3u/platform/tuturuuu-web-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 28 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 29 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00023 | $0.00530 |
| Opus 5.5 | $0.00009 | $0.00212 |
| Sonnet 5.5 | $0.00005 | $0.00106 |
| Haiku 4.5 | $0.00002 | $0.00053 |
Grade A, and why
tuturuuu-web-release 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tuturuuu Web Release
Use this skill when touching the apps/web version badge, platform release
metadata, Docker blue/green deployment metadata, release docs, or release-please
version metadata.
Core Rules
- Treat
TUTURUUU_PLATFORM_VERSIONin@tuturuuu/utils/platform-releaseas the displayed platform badge version. Do not manually bump it for ordinary authored commits; Release Please updates it fromplatform-version.txt. - Keep the
x-release-please-versioncomments on the platform version constant and matching test expectation. The monorepo release-please config also keepsplatform-version.txtaligned for theplatformrelease component. - Do not bump
apps/web/package.jsonfor badge/version display unless the user explicitly asks for package metadata changes. - Preserve the account gate: only exact
@tuturuuu.comusers can see/manage the badge, and the user setting remains opt-in. - Preserve the bottom-right compact badge and hover/focus details unless the user explicitly asks for a visual redesign.
- Read only lightweight blue/green runtime files for self-hosted inference:
prod/target-state.json,prod/active-color,prod/deployment-stamp,watch/blue-green-auto-deploy.status.json, andwatch/blue-green-auto-deploy.history.json.
Metadata Precedence
For apps/web, keep metadata precedence stable:
- Explicit
PLATFORM_BUILD_*runtime environment values. - Mounted blue/green runtime snapshot via
PLATFORM_BLUE_GREEN_MONITORING_DIR, with localtmp/docker-webfallbacks for development. - Generated Vercel/GitHub build metadata.
- Existing local defaults.
Do not invent deployment URL, ref, or environment from active color, commit hash, or deployment stamp alone. Use those fields only when an explicit env, runtime row, status snapshot, or generated metadata provides them.
builtAt means the checked-out source commit timestamp. Do not populate it
from deployment start, finish, activation, promotion, or wall-clock time. Keep
those deployment timestamps in GitHub/Vercel records and blue/green history.
What ships with it
2 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.
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 Changed · -30 tokens per session 5124ef76b0af
- 1mo ago First seen · 54 lines · 53 tokens per session scan A 5dd65d2123c1
tuturuuu-web-release is a skill published in the GitHub repository tutur3u/platform (55 stars, last pushed yesterday), licensed Apache-2.0. It adds 23 tokens to every session and 530 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 2026-09-03.
Other skills, from other repositories
draft-release-notes
Author the committed release-notes file for a Prisma 8 release (stable or 8.0.0-rc.N) by enumerating the merged PRs since the previous release v tag (stable or -rc.N), resolving opaque TML-NNNN: titles via Linear context (never copied verbatim), triaging public-worthiness, and writing categorized notes — breaking…
publish-npm-version
Cuts the next release of Prisma 8: bumps the root package.json version (on the v8 RC line: 8.0.0-rc.N → rc.N+1), propagates it to every workspace package, and opens a PR titled "chore(release): bump to ". When the maintainer merges the PR, the Publish to npm workflow runs automatically and ships the new version to npm…
create-draft-pr
Create a draft pull request for the current session. Use when the user wants to open a draft PR with the session's changes.
create-pr
Create a pull request for the current session. Use when the user wants to open a PR with the session's changes.
magic-ui
Use this skill when users want to add, customize, or troubleshoot Magic UI components in React/Next.js projects. It covers component selection, shadcn registry installation (@magicui/), integration patterns, and practical quality checks for accessibility and maintainability.
publish-notes
Draft user-facing release notes, store changelogs, and internal publish summaries.