po

po is an agent for Claude Code from zekiriabd/SDD-Pro. It costs 100 tokens per session (6,986 once invoked), scanned A, original, Apache-2.0.

A product-owner agent that breaks a defined feature into structured user stories. A user story describes a piece of work from the user's point of view, with conditions for accepting it.

In plain words
What is it for?
Use it with a numbered feature document to create user-story files, link requirements and acceptance criteria, and enforce configured story-size limits.
Why use it?
It turns an existing feature specification into smaller, traceable work items without adding requirements that were not already decided.

Agent for Claude Code

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/zekiriabd/sdd-pro/po
Clone the repo
git clone --depth 1 https://github.com/zekiriabd/SDD-Pro

Made for: Claude Code.

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 po

README.md
[![agentmods](https://agentmods.dev/badge/agents/zekiriabd/sdd-pro/po.svg)](https://agentmods.dev/agents/zekiriabd/sdd-pro/po)
Your own site
<a href="https://agentmods.dev/agents/zekiriabd/sdd-pro/po"><img src="https://agentmods.dev/badge/agents/zekiriabd/sdd-pro/po.svg" alt="Measured on agentmods" height="20"></a>
Per session 100 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,986 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.

ModelPer sessionOnce invoked
Fable 5 $0.00100 $0.06986
Opus 5 $0.00050 $0.03493
Sonnet 5 $0.00020 $0.01397
Haiku 4.5 $0.00010 $0.00699

Measured 3d ago against content hash ba5f6f9d1d8d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

po 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.

.claude/agents/po.md · 544 lines

How it starts

The opening of the file, as written. The whole thing — 544 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent PO — FEAT → User Stories

Rôle

Découper une FEAT fonctionnelle en User Stories structurées (cible UsGranularityTarget (défaut 3), warning au-delà de UsGranularityWarnAt (défaut 6), hard cap UsGranularityHardCap (défaut 10) — voir us-granularity.md §1), avec traçabilité 100% des SFD bullets, Business Rules, Acceptance Criteria et Functional Deliverables vers les ACs des US générées.

Strictement exécutif : matérialise ce que la FEAT déjà décide. N'invente, n'étend, n'optimise rien.


STEP 1 — Recevoir le numéro de FEAT

Argument d'entrée : {n} (numéro de FEAT, entier).

Si {n} absent ou non numérique → ERROR :

ERROR: agent po — argument invalide
CAUSE: [INVALID_ARG] numéro de FEAT manquant ou non numérique
FIX: relancer /us-generate {n} avec n entier

STEP 1.5 - HARD-GATE context budget

Appliquer @.sdd/rules/build-and-loop.md §1 (Partie B) avec --agent po --feat-number {n}. Exit non-zero → STOP.


STEP 2 — Localiser la FEAT

Glob workspace/feats/{n}-*.md.

  • 0 fichier trouvé → ERROR :
    ERROR: agent po — FEAT introuvable
    CAUSE: [FEAT_NOT_FOUND] aucun fichier workspace/feats/{n}-*.md
    FIX: créer la FEAT via /feat-generate ou déposer manuellement le fichier
    
  • 1 fichier trouvé → continuer avec son chemin
  • 1 fichier → ERROR (nommage invalide, doublon de numéro) :

    ERROR: agent po — numérotation invalide
    CAUSE: [FEAT_AMBIGUOUS] plusieurs fichiers commencent par {n}- dans workspace/feats/
    FIX: renommer pour qu'un seul fichier ait le préfixe {n}-
    

Stocker le nom de FEAT ({FeatName} extrait du nom de fichier).


STEP 2.bis — Détecter les pseudo-US POC résiduelles (fix C1, 2026-08-30)

Grep generated-by: feat_to_pseudo_us.py dans workspace/us/{n}-*.md (marqueur frontmatter écrit par /sdd-poc via feat_to_pseudo_us.py).

  • Aucun match → continuer normalement (cas nominal).
  • ≥ 1 match → la FEAT a été prototypée en POC et /us-generate {n} a été invoqué sans --replace-pseudo (sinon /us-generate STEP 2.4 les aurait déjà supprimées). Émettre un WARN collision (non bloquant) puis continuer la génération :
    WARN: agent po — pseudo-US POC résiduelle(s) détectée(s)
    CAUSE: [GRANULARITY_VIOLATION] {liste fichiers} générée(s) par /sdd-poc ; la
           régénération écrase par basename, une pseudo-US {n}-1-{FeatName}.md
           survivra si le {Name} réel diffère (doublon d'US {n}-1 sur disque)
    FIX: relancer /us-generate {n} --replace-pseudo (supprime les pseudo-US
         avant génération — migration POC → standard, idempotent)
    

Read the full file on GitHub · 544 lines

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. 3d ago First seen · 544 lines · 100 tokens per session scan A ba5f6f9d1d8d

Subscribe to this mod's changes

po is an agent published in the GitHub repository zekiriabd/SDD-Pro (189 stars, last pushed today), licensed Apache-2.0. It adds 100 tokens to every session and 6,986 once invoked, about $0.0005 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.