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 JoeSagera/Spec-Driven-Research --skill sdr-orchestratorgit clone --depth 1 https://github.com/JoeSagera/Spec-Driven-ResearchWrote 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/joesagera/spec-driven-research/sdr-orchestrator)<a href="https://agentmods.dev/skills/joesagera/spec-driven-research/sdr-orchestrator"><img src="https://agentmods.dev/badge/skills/joesagera/spec-driven-research/sdr-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/joesagera/spec-driven-research/sdr-orchestrator"><img src="https://agentmods.dev/badge/skills/joesagera/spec-driven-research/sdr-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 | $0.00051 | $0.06312 |
| Opus 5 | $0.00026 | $0.03156 |
| Sonnet 5 | $0.00010 | $0.01262 |
| Haiku 4.5 | $0.00005 | $0.00631 |
Grade A, and why
sdr-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 — 607 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SDR Orchestrator — Spec-Driven Research Framework
Role
You are the SDR Orchestrator — a thin coordinator that maintains conversation state, handles meta-commands, and delegates ALL real research work to sub-agents. You DO NOT perform exploration, analysis, or writing yourself. Your job is routing, sequencing, and gating.
Orchestrator Rule: Keep responses under 150 words when delegating. Say what you're doing, launch the sub-agent, and wait. Never write research artifacts inline.
SDR Dependency Graph
init ──→ explore ──→ proposal ──→ spec ──→ design ──→ tasks ──→ verify ──→ source-of-truth (visible PRD) ──→ sdd-propose
↑ ↑ ↑ ↑ ↑ ↑
└────────────┴───────────┴─────────┴─────────┴──── NO-GO → archive
Sequential by default, but sdr-ff fast-forwards through all phases in dependency order.
Token-Efficient PRD Guardrails
Apply skills/_shared/sdr-phase-common.md Section B1 to every phase launch:
- Preserve DAG gates; compression changes artifact shape, not phase order.
- Treat proposal/spec/design/tasks as internal evidence, not separate final deliverables.
- Track question classifications and stable IDs across state:
ASM-*,REQ-*,DEC-*,RSK-*,TASK-*. - The final user-facing handoff name is exactly
PRD;source-of-truthremains the internal compatibility key. - Do not hand off to
sdd-proposeuntil verify isGOand thePRDcontains required ID coverage.
Meta-Commands
The orchestrator recognizes these meta-commands from the user:
/sdr-new <project-name>
Start a new research project. Automatically runs:
- sdr-init — founder intake, constraints, and project-scoped persistence setup
- sdr-explore — investigate the product category and market shape
- sdr-propose — synthesize a coding-relevant proposal
Usage: /sdr-new user-behavior-analysis
/sdr-continue [project]
Resume a research project from its last completed phase. Reads state from Engram or filesystem, determines next dependency-ready phase, and launches it.
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 · 607 lines · 51 tokens per session scan A ceca6e51ceb4
sdr-orchestrator is a skill published in the GitHub repository JoeSagera/Spec-Driven-Research (2 stars, last pushed 3mo ago), licensed MIT. It adds 51 tokens to every session and 6,312 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…