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 skills/siva01c/claude-plugins/deploy-workflownpx skills add siva01c/claude-plugins --skill deploy-workflowgit clone --depth 1 https://github.com/siva01c/claude-pluginsWhat 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 | $0.00092 | $0.00997 |
| Opus 5 | $0.00046 | $0.00498 |
| Sonnet 5 | $0.00018 | $0.00199 |
| Haiku 4.5 | $0.00009 | $0.00100 |
Grade A, and why
deploy-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 3d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deploy Workflow
Deployment of a Drupal site has a fixed order of operations. Skipping a step or reordering it produces failures that only surface at runtime. This skill enforces the sequence and its preconditions.
When this activates
- Deploying a Drupal codebase to staging or production
- Running a release on a multisite platform
- Applying core or contrib updates on a server
- The user asks to push changes live or update an environment
Phase 0 — Pre-flight (before touching the target)
- Confirm the target: which environment, which drush alias or SSH host. Never assume production.
- Verify the working tree being deployed is clean and on the intended tag/branch.
- Check config status on the target:
drush config:status. Unexpected overrides on the target mean someone changed config in the UI — resolve before deploying, or the import will silently destroy their changes. - Maintenance window: for schema-changing releases, ask whether maintenance mode is required (
drush state:set system.maintenance_mode 1).
Exit condition: target confirmed by the user, config status reviewed.
Phase 1 — Backup
drush @TARGET sql:dump --result-file=auto --gzip
Also snapshot the current codebase reference (deployed tag/commit) so rollback is a known state, not a guess.
Exit condition: a restorable database dump exists and its location is recorded.
Phase 2 — Deploy sequence
The canonical order:
git fetch && git checkout TAG # or the platform's deploy mechanism
composer install --no-dev --optimize-autoloader
drush deploy # = updb + cim + cr + deploy:hook (Drush 10.3+)
If drush deploy is not available or the project needs explicit control:
drush updb -y # database updates first — update hooks may rely on old config
drush cim -y # import configuration
drush cr # rebuild caches
drush deploy:hook -y # post-deploy hooks, if used
Notes:
- If an update hook depends on new config being present, that is a design smell — prefer
hook_post_updateorhook_deploy_NAME(); do not hand-reorder cim before updb as a workaround without understanding why. - Multisite: run the update sequence per site:
drush -l SITE updb -y && drush -l SITE cim -y && drush -l SITE crfor every site sharing the codebase. A release is not done until every site has been updated.
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.
- 3d ago First seen · 93 lines · 92 tokens per session scan A fb2ad5d78404
deploy-workflow is a skill published in the GitHub repository siva01c/claude-plugins (16 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 997 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
iflytek-hyper-tts
Use when user asks to synthesize speech, convert text to audio, or read text aloud. 讯飞超拟人语音合成 - 支持文本转语音、语音合成(发音人/语速/语调/音量/输出格式)。大模型语音合成技能。语音合成, 文字转语音, 超拟人, TTS.
iflytek-ocr-invoice
Use when user asks to recognize invoices, extract receipt data, or OCR bills and tickets. Recognize and extract structured data from invoices, receipts, and bills using iFlytek OCR API (科大讯飞票据识别). Supports VAT invoices, taxi receipts, train tickets, toll invoices, medical bills, bank receipts, and more.
iflytek-voiceclone-tts
Use when user asks to clone a voice, train a custom voice model, or synthesize speech with a cloned voice. iFlytek Voice Clone tts(声音复刻) — train a custom voice model from audio samples and synthesize speech with the cloned voice. Supports the full workflow: get training text → create task → upload audio → submit…
animated-sketch-diagram
生成"黑墨手绘涂鸦"风格的动画架构图/流程图:米色纸面、针管笔墨线、极淡水洗色块、简笔涂鸦图标、序号章、连线上的流动圆点动画、图标微动效。产出单文件自包含动画 HTML(SVG+CSS),可一键导出无缝循环 GIF。当用户想画架构图、流程图、信息图、技术示意图、对比图、pipeline/workflow 可视化,或提到"手绘风""涂鸦风""动图""animated diagram""GIF 架构图"时使用;即使用户没明说要动画,做技术概念科普配图时也应优先考虑本 skill。.
iflytek-pdf-image-ocr
AI-powered OCR service for images and PDF documents using iFlytek's advanced recognition APIs.
iflytek-text-proofread
Proofread Chinese text using iFlytek's Official Document Proofreading API (公文校对). Detects 27 types of errors across three categories.