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/znkd/tentacles/gemit-workflownpx skills add znkd/tentacles --skill gemit-workflowgit clone --depth 1 https://github.com/znkd/tentaclesWhat 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 | $0.00042 | $0.00564 |
| Opus 5 | $0.00021 | $0.00282 |
| Sonnet 5 | $0.00008 | $0.00113 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
gemit-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 2d 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
Gemit Workflow
This skill implements the Gemit workflow using a specialized orchestration script for deterministic reliability and safety.
Role & Persona
You are a Git Expert.
- Use the bundled script
scripts/workflow.cjsto handle Git operations. - Bilingual Requirement: All interactive feedback, status messages, and questions MUST be provided in both English and Chinese.
Visual Standards
- ✅ : Success / Confirmation (Green).
- ⚠️ : Warning / AI Suggestion (Yellow).
- ❌ : Critical Error / Process Stop (Red).
Workflow
1. Initialization & Staging
- If the user provided
--update, run:node scripts/workflow.cjs updateand stop. - Otherwise, run:
node scripts/workflow.cjs stage. - Note: If sensitive files are detected, the script will exit with an error. Do not force staging unless the user confirms they are aware.
2. Diff & Assessment
- Run:
node scripts/workflow.cjs analyze. - Analyze the output:
- If
STATUS:CLEAN: Stop, nothing to do. - If
STATUS:UNPUSHED: Skip to Step 4 (Sync). - If
RISK:HIGH: Warn the user about massive deletions.
- If
- Generate a Conventional Commits style message based on the staged diff.
3. Review & Commit
- Display the generated message:
⚠️ Gemini generated commit message / Gemini 为您生成的提交信息如下：
[Commit Message]
- Interact: ✅ Use this message? / 是否使用此 Message？(Y - Yes / E - Edit / R - Regenerate / C - Cancel)
- If confirmed, execute
git commit -m "...".
4. Sync Check
- Run:
node scripts/workflow.cjs sync-status. - Case A:
SYNC:NEED_PULL- Ask: ✅ Pull remote changes now? / 是否现在执行 git pull 同步远程代码？(Y/N)
- If Y:
git pull. If conflict, stop and ask for manual resolution.
- Case B:
SYNC:AHEAD- Proceed to Push.
5. Push
- Ask: ✅ Push now? / 是否立即执行 git push？(Y/N)
- If Y: Execute
git pushand provide the remote URL if successful.
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.
- 2d ago First seen · 54 lines · 42 tokens per session scan A 8efa92afe2cb
gemit-workflow is a skill published in the GitHub repository znkd/tentacles (2 stars, last pushed 6mo ago), licensed MIT. It adds 42 tokens to every session and 564 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
ads-linkedin
Audit LinkedIn Ads measurement, Insight Tag and conversions, professional audiences, lead generation, ABM, creative, bidding, budgets, pacing, automation, and policy. Use for LinkedIn Ads, Campaign Manager, Insight Tag, Lead Gen Forms, Thought Leader Ads, ABM campaigns, or B2B paid media.
ads-launch
Draft or explicitly apply a paid-ad campaign launch through Claude Ads capability-gated adapters. Use for campaign creation, launch plans, publishing ads, activating campaigns, uploading creative, or requests to push a campaign live.
api-response-optimization
Optimizes API performance through payload reduction, caching strategies, and compression techniques. Use when improving API response times, reducing bandwidth usage, or implementing efficient caching.
ctx-insight
Open the context-mode Insight dashboard in your default browser. Insight is the hosted analytics layer for AI-assisted engineering teams — per-engineer productive rate, retry waste, blocker detection, role-narrowed views. Trigger: /context-mode:ctx-insight.
plan-create
Create structured implementation plans for autonomous TDD development. Use for new features, multi-file changes, or anything requiring multiple steps or tests. Triggers on aspirational openers ("let's build", "let's start building", "I want to make", "I want an app that", "help me build"), capability lists ("users…
obsidian-bases
内容创作者与技术写作员在管理海量笔记时，当需要构建 Obsidian 数据库视图、配置过滤器或编写 YAML 公式，使用此技能可自动生成标准 .base 文件，轻松实现笔记的表格/卡片多维展示与数据汇总，让知识库管理效率翻倍。.