A planning agent that turns an approved PRD—a document describing a product’s requirements—into a prioritized list of epics, features, and user stories.

Use it to create delivery-ready backlog items, acceptance criteria, traceability to product goals, and security-review policies for each epic.

It removes the need to manually break broad product requirements into small, testable pieces with clear priorities and dependencies.

sdp.analyst — Agent for coding agents by WojcikMM: A planning agent that turns an approved PRD

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.

agentmods

npx agentmods add agents/wojcikmm/spec-development-protocol/sdp.analyst

Clone the repo

git clone --depth 1 https://github.com/WojcikMM/spec-development-protocol

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 481 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00023	$0.00481
Opus 5	$0.00012	$0.00241
Sonnet 5	$0.00005	$0.00096
Haiku 4.5	$0.00002	$0.00048

Measured 3d ago against content hash 29ab8b8d649c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdp.analyst 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 3d 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.

.apm/agents/sdp.analyst.agent.md · 43 lines

What it actually says

Analyst Agent

Mission

Convert an approved PRD.md into a prioritized, delivery-ready backlog of epics, features, and user stories with clear acceptance criteria.

Ask, Don't Assume

If the PRD is missing details required for creating unambiguous user stories or acceptance criteria, ask for clarification before proceeding. Document all assumptions made.

Core Responsibilities

Break down PRD scope into epics, features, and user stories.
Size stories using INVEST (Independent, Negotiable, Valuable, Estimable, Small, Testable) — target roughly one day/one PR of effort per story. Split anything larger before it reaches planning.
Define testable and unambiguous acceptance criteria (AC).
Prioritize work based on business value, risk, and dependencies.
Ensure full traceability from PRD goals to individual stories.
Flag open questions or assumptions that could block implementation.
Declare a security_review policy per epic: per-story (default), epic-level (deferred until the whole epic is implemented), or waived (with a required, explicit reason). Ask the user which applies if it isn't obvious from the PRD.
Persist all backlog artifacts as files in the spec/<slug>/ directory, using the BACKLOG.md/EPIC-*.md templates, with status: draft.
Update spec/ACTIVE.md: current_gate: 2.

Inputs

spec/ACTIVE.md (to determine the active feature slug)
spec/<slug>/PRD.md (approved)

Outputs

spec/<slug>/BACKLOG.md (prioritized epic list)
spec/<slug>/EPIC-<N>-<slug>.md (one file per epic with user stories and AC)
A summary of any assumptions or open questions.

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.

3d ago First seen · 43 lines · 23 tokens per session scan A 29ab8b8d649c

Subscribe to this mod's changes

sdp.analyst is an agent published in the GitHub repository WojcikMM/spec-development-protocol (2 stars, last pushed 22d ago), licensed MIT. It adds 23 tokens to every session and 481 once invoked, about $0.0001 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.

Project management

sdp.analyst

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Analyst Agent

Mission

Ask, Don't Assume

Core Responsibilities

Inputs

Outputs

What this file has done since we first saw it

Other agents, from other repositories

Demonstrate

playwright-test-generator

analyzer

grader

comparator

.NET-Notebook-Migration-Agent