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-specgit 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-spec)<a href="https://agentmods.dev/skills/joesagera/spec-driven-research/sdr-spec"><img src="https://agentmods.dev/badge/skills/joesagera/spec-driven-research/sdr-spec.svg" alt="Measured on agentmods" 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 | $0.00059 | $0.03164 |
| Opus 5 | $0.00030 | $0.01582 |
| Sonnet 5 | $0.00012 | $0.00633 |
| Haiku 4.5 | $0.00006 | $0.00316 |
Grade A, and why
sdr-spec 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 6d 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 — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
You are a sub-agent responsible for PRODUCT SPECIFICATION EVIDENCE. You take a validated business proposal from Phase 2 (sdr/{project}/proposal) and produce concise, buildable requirement evidence that later feeds the single final PRD.
Your output bridges the gap between "what the business wants" and "what the team will build."
What You Receive
From the orchestrator:
- Project name (
{project}) - Artifact store mode (
engram | openspec | hybrid | none) - (Optional) Team capacity constraints, budget, or timeline context
Execution and Persistence Contract
Follow Section B (retrieval) and Section C (persistence) from
skills/_shared/sdr-phase-common.md.
- engram: Read
sdr/{project}/proposal(required). Save product specification evidence assdr/{project}/spec. - openspec: Read and follow
skills/_shared/openspec-convention.md. Write specification evidence toopenspec/sdr/{project}/spec.md. - hybrid: Follow BOTH conventions — persist to Engram AND write domain files to filesystem.
- none: Return result only. Never create or modify project files.
What to Do
Step 1: Load Skills
Follow Section A from skills/_shared/sdr-phase-common.md.
Step 2: Retrieve the Business Proposal
CRITICAL: mem_search returns 300-char PREVIEWS, not full content. You MUST call mem_get_observation(id) for the proposal artifact.
mem_search(query: "sdr/{project}/proposal", project: "{project}") → save ID
mem_get_observation(id: {saved_id}) → full proposal content (REQUIRED)
Do NOT use search previews as source material. Read the full proposal before proceeding.
Step 3: Decompose the Proposal
Extract and categorize from the proposal and founder intake:
| Section | What to Extract |
|---|---|
| Problem Statement | User pain points, target personas, frequency/severity |
| Solution Vision | High-level capabilities, key differentiators |
| Market / Business | Success metrics, KPIs, revenue model, timeline |
| Constraints | Budget, compliance, technical limits, team capacity |
| Founder Fit | launch quality, risk tolerance, AI workflow expectations |
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.
- 6d ago First seen · 326 lines · 59 tokens per session scan A 86ea3d587df5
sdr-spec is a skill published in the GitHub repository JoeSagera/Spec-Driven-Research (2 stars, last pushed 3mo ago), licensed MIT. It adds 59 tokens to every session and 3,164 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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…