agentmods.dev

takomi

takomi is a skill for Claude Code, Codex from J-StaR-Films-Studios/VibeCode-Protocol-Suite. It costs 32 tokens per session (650 once invoked), scanned A, original, ISC.

A workflow for coordinating multi-stage work through Takomi stages such as genesis, design, build, review, and finalization.

In plain words
What is it for?
Use it to start Takomi workflows, coordinate several project stages, or move an agent through its lifecycle.
Why use it?
It gives complex work a defined sequence and helps track the agent's stage in the process.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 24repo yesterday A scan SkillSpector: pass 32 tokens original ISC

Good fit Use it to start Takomi workflows, coordinate several project stages, or move an agent through its lifecycle.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/j-star-films-studios/vibecode-protocol-suite/takomi
View source ↗ J-StaR-Films-Studios/VibeCode-Protocol-Suite
Install

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.

Any agent
npx skills add J-StaR-Films-Studios/VibeCode-Protocol-Suite --skill takomi
Clone the repo
git clone --depth 1 https://github.com/J-StaR-Films-Studios/VibeCode-Protocol-Suite

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for takomi

README.md
[![agentmods](https://agentmods.dev/badge/skills/j-star-films-studios/vibecode-protocol-suite/takomi/github.svg)](https://agentmods.dev/skills/j-star-films-studios/vibecode-protocol-suite/takomi)
Your own site
<a href="https://agentmods.dev/skills/j-star-films-studios/vibecode-protocol-suite/takomi"><img src="https://agentmods.dev/badge/skills/j-star-films-studios/vibecode-protocol-suite/takomi/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.

agentmods 80×15 button for takomi

Your own site · 80×15
<a href="https://agentmods.dev/skills/j-star-films-studios/vibecode-protocol-suite/takomi"><img src="https://agentmods.dev/badge/skills/j-star-films-studios/vibecode-protocol-suite/takomi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 650 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.00650
Opus 5 $0.00016 $0.00325
Sonnet 5 $0.00006 $0.00130
Haiku 4.5 $0.00003 $0.00065

Measured 8d ago against content hash d769911b269a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

takomi 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 8d 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.

assets/.agent/skills/takomi/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Takomi (Unified Skill)

This single skill contains the full non-legacy Takomi workflow suite. Use it whenever a user says "use takomi", asks for Vibe Code lifecycle execution, or references any prior workflow names.

How To Use

  • Natural language is primary. Slash commands are optional and not required.
  • Examples:
    • use takomi
    • use takomi genesis
    • run vibe genesis
    • continue build with takomi

Router Behavior

  1. Match user intent to one workflow playbook from workflows/.
  2. Execute that playbook's protocol.
  3. Recommend the next workflow stage after completion.
  4. Allow explicit user overrides (guided gates, not hard blocks).

Lifecycle Gates

  • Discover/Prime: vibe-primeAgent.md, reverse_genesis.md
  • Plan/Design: vibe-genesis.md, vibe-design.md, mode-architect.md, mode-visionary.md
  • Build/Continue: vibe-build.md, vibe-continueBuild.md, mode-code.md, stitch.md, remotion-build.md
  • Review/Finalize: mode-review.md, review_code.md, vibe-finalize.md, vibe-syncDocs.md
  • Recovery/Migration: agent_reset.md, escalate.md, migrate.md, optimize-agent-context.md, mode-orchestrator.md, mode-debug.md, mode-ask.md, vibe-spawnTask.md, spawn-jstar-code-review.md

Workflow Playbooks (Contained In This Skill)

  • workflows/vibe-genesis.md
  • workflows/vibe-design.md
  • workflows/vibe-build.md
  • workflows/vibe-continueBuild.md
  • workflows/vibe-finalize.md
  • workflows/vibe-primeAgent.md
  • workflows/vibe-spawnTask.md
  • workflows/vibe-syncDocs.md
  • workflows/reverse_genesis.md
  • workflows/mode-orchestrator.md
  • workflows/mode-architect.md
  • workflows/mode-code.md
  • workflows/mode-debug.md
  • workflows/mode-ask.md
  • workflows/mode-review.md
  • workflows/mode-visionary.md
  • workflows/review_code.md
  • workflows/spawn-jstar-code-review.md
  • workflows/agent_reset.md
  • workflows/escalate.md
  • workflows/migrate.md
  • workflows/optimize-agent-context.md
  • workflows/stitch.md
  • workflows/remotion-build.md

Read the full file on GitHub · 62 lines

Files

What ships with it

25 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.

Changes

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.

  1. 8d ago First seen · 62 lines · 32 tokens per session scan A d769911b269a

Subscribe to this mod's changes

takomi is a skill published in the GitHub repository J-StaR-Films-Studios/VibeCode-Protocol-Suite (24 stars, last pushed yesterday), licensed ISC. It adds 32 tokens to every session and 650 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 2026-09-03.

Project managementaiai-agentsprompt-engineering
Related

Other skills, from other repositories

wayfinder

A planning method for large or unclear work that maps the decisions needed between the current situation and a defined destination. It records the map and decision tickets in an issue tracker.

devcxl/mattpocock-skills-zh · 57 tokens

triage

A structured issue-triage process that moves issues and, where configured, pull requests through classification and status steps. Triage means deciding what a report is, whether more information is needed, and who should handle it.

devcxl/mattpocock-skills-zh · 39 tokens

plan-to-tickets

Use when a large plan, PRD, feature, refactor, research plan, or multi-step coding task must be split into small ready-for-agent tickets with acceptance criteria, verification commands, blockers, and vertical tracer-bullet slices. Do not use for small tasks that should be implemented directly, single-bug fixes, or…

AnastasiyaW/codex-claude-code-config · 74 tokens

to-tickets

A method for turning a plan, specification, or conversation into small work tickets that each deliver a complete, testable slice of functionality. Each ticket records which other tickets must be finished first.

devcxl/mattpocock-skills-zh · 71 tokens

to-spec

A method for turning the current conversation and codebase understanding into a detailed software specification, then publishing it as an issue in the project’s issue tracker. An issue tracker is a tool for recording and managing development work.

devcxl/mattpocock-skills-zh · 33 tokens

alterlab-grant-reporting

Drafts post-award grant deliverables across funder formats — NIH RPPR (Annual/Interim/Final via eRA Commons), NSF annual/final project reports and the public Project Outcomes Report (Research.gov), and Horizon Europe / ERC periodic and final reports (technical Part A/B + financial statements on the EU Funding &…

AlterLab-IEU/AlterLab-Academic-Skills · 203 tokens