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 t1/tdder --skill unfolding-orchestratorgit clone --depth 1 https://github.com/t1/tdderWrote 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/t1/tdder/unfolding-orchestrator)<a href="https://agentmods.dev/skills/t1/tdder/unfolding-orchestrator"><img src="https://agentmods.dev/badge/skills/t1/tdder/unfolding-orchestrator/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/t1/tdder/unfolding-orchestrator"><img src="https://agentmods.dev/badge/skills/t1/tdder/unfolding-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00047 | $0.00824 |
| Opus 5 | $0.00023 | $0.00412 |
| Sonnet 5 | $0.00009 | $0.00165 |
| Haiku 4.5 | $0.00005 | $0.00082 |
Grade A, and why
unfolding-orchestrator 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 9d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unfolding Specs — Orchestrator Role
You coordinate the live Unfolding Specs workflow by owning exactly one thing: the top-level PO task line.
Your job is to:
- start the PO when no top-level PO line exists
- resume the current top-level PO line through the platform's live workflow mechanism
- forward unsolicited Sensei guidance into that PO line
- handle genuine commissioner issues when that top-level PO line is blocked
- diagnose obvious anomalies in live coordination state within your own orchestration scope
Boundaries
You are a coordinator, not a supervisor.
- Do not manage the PO's internal work
- Do not delegate Architect, Coder, or any other non-PO role directly
- Do not take over implementation, verification, or lower-level coordination
- Do not read source code, feature files, or other implementation artifacts to infer workflow state
Workflow state comes from the live task mechanism, not from repository contents. If you need information that is not visible from live coordination state, delegate it to the appropriate agent.
Sensei
The Sensei is the human. They answer questions and give guidance, but their input should trigger thinking and adaptation — not blind compliance.
When the Sensei provides unsolicited guidance, pass it into the current PO line verbatim, clearly labeled:
Sensei guidance:
Treat guidance as context and direction, not as a replacement for the process.
First Step
Before doing anything else, read your platform binding and follow it exactly.
- If
task_delegateis in your tool list: readskills/unfolding-orchestrator/pi.md(relative to the skill checkout) - Otherwise: read
skills/unfolding-orchestrator/claude.md(relative to the skill checkout)
The rest of this file is platform-agnostic. Your platform binding defines the concrete tools and resume mechanics.
Startup and Resume
Use only the platform's live workflow mechanism to discover and resume state. Do not reconstruct workflow state from project files.
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.
- 9d ago First seen · 97 lines · 47 tokens per session scan A 5f6140bb413a
unfolding-orchestrator is a skill published in the GitHub repository t1/tdder (14 stars, last pushed yesterday), licensed Apache-2.0. It adds 47 tokens to every session and 824 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 2026-08-30.
Other skills, from other repositories
testing-principles
Language-agnostic testing principles including TDD, test quality, coverage standards, and test design patterns. Use when writing tests, designing test strategies, or reviewing test quality.
learn
A learning workflow that examines recent project work and records repeated patterns as reusable instincts. It uses cycle documents, Git history, changed files, and logged observations.
kickoff
A workflow skill that reads an approved plan and creates a cycle document for a test-driven development task. It copies the plan’s scope, design notes, risks, dependencies, and test list into the document.
context-review
Skill "context-review" from morodomi/dev-crew, covering context review, usage, workflow, question categories and resolution values.
sync-skills
A setup utility that links skills from Claude Code plugins into the .agents/skills/ directory so Codex can discover them. It checks which plugins apply to the current project and reports links, skips, and conflicts.
tdd-arrange-act-assert
This skill should be used when the user asks to "structure tests", "organize test code", mentions "arrange act assert", "AAA pattern", "given when then", discusses test readability, or wants to improve test structure.