A procedure for carrying out an already approved software-development task described in an SDD, or software design document. It keeps the implementation tied to the approved requirements and checks the result with tests.

Use it to implement approved features from task files, follow project-specific guidance, update task status, and provide evidence that the change works.

It prevents an agent from starting unapproved work or drifting beyond the agreed task while coding.

sdd-exec — Skill for Claude Code and Codex by felipefontoura

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.

Any agent

npx skills add felipefontoura/pi-sdd-kit --skill sdd-exec

Clone the repo

git clone --depth 1 https://github.com/felipefontoura/pi-sdd-kit

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/felipefontoura/pi-sdd-kit/sdd-exec.svg)](https://agentmods.dev/skills/felipefontoura/pi-sdd-kit/sdd-exec)

Your own site

<a href="https://agentmods.dev/skills/felipefontoura/pi-sdd-kit/sdd-exec"><img src="https://agentmods.dev/badge/skills/felipefontoura/pi-sdd-kit/sdd-exec.svg" alt="Measured on agentmods" height="20"></a>

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 955 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00064	$0.00955
Opus 5	$0.00032	$0.00477
Sonnet 5	$0.00013	$0.00191
Haiku 4.5	$0.00006	$0.00096

Measured 7d ago against content hash 14d794cd4dea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

sdd-exec 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 7d 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.

skills/sdd-exec/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SDD Exec

Implement approved tasks while preserving traceability to requirements and design.

Purpose

Execution turns approved specs into code. The agent must stay within the task scope, follow project conventions, verify the result, and update task status only when evidence exists. Because this edits production code, use it only after an explicit user request to execute or implement approved SDD work.

Workflow

Load the SDD reference.
- Read ../_shared/references/sdd-practical.md.
- Apply the Language Policy: respond and write artifacts in the user's initial chat language while keeping skill instructions and templates in EN-US.
- Load relevant .ai/steering/*.md files when present, especially tech-stack.md, conventions.md, and principles.md.
Locate the feature and task, then validate the gate.
- Use .ai/sdd/specs/NNN-feature-name/.
- Read .status.
- Validate .status against the official status values from sdd-practical.md.
- If .status is missing or invalid, stop and ask the user to repair it; do not infer task approval from tasks.md existing.
- Block if status is not tasks:approved or implementation:in-progress, unless the user explicitly requests a spike.
- If blocked, report the current status and recommend /skill:sdd-tasks approval as the next safe action.
- Read requirements.md, design.md, tasks.md, and decisions.md if present.
- Identify the requested task. If no task is specified, select the first incomplete task whose dependencies are complete and confirm with the user.
Reconcile workspace state.
- Inspect current files before editing.
- Do not overwrite user changes.
- If unexpected edits overlap with the task, stop and ask how to proceed.
Build an execution checklist.
- Extract task work items, acceptance criteria, file targets, and verification items.
- Print the checklist before editing.
- Set .status to implementation:in-progress when starting implementation from tasks:approved.
- If already implementation:in-progress, preserve that status while continuing incomplete approved tasks.

Read the full file on GitHub · 88 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.

7d ago First seen · 88 lines · 64 tokens per session scan A 14d794cd4dea

Subscribe to this mod's changes

sdd-exec is a skill published in the GitHub repository felipefontoura/pi-sdd-kit (22 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 955 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 2026-08-30.

Claude Code Planning ai-agents pi-agent pi-dev pi-package skills

surf

Control Chrome browser via CLI for testing, automation, and debugging. Use when the user needs browser automation, screenshots, form filling, page inspection, network/CPU emulation, DevTools streaming, or AI queries via ChatGPT/Gemini/Perplexity/Grok/AI Studio.

w-winter/dot314 · 60 tokens

prose-review

Review prose written for others (e.g., user-facing documentation, prompts for other LLMs, reports, plans, inline comments, docstrings) for local jargon leakage, orphaned references, missing grounding, and audience or genre mismatch. Always run on prose you produce or materially edit, except for routine conversational…

w-winter/dot314 · 84 tokens

text-search

Search indexed text corpora with qmd. For indexed content, prefer qmd over grep.

w-winter/dot314 · 22 tokens

repoprompt-tool-guidance-refresh

Refresh RepoPrompt tool guidance when the CLI/MCP surface changes. Tracks RepoPrompt CE (rpce-cli, the maintained target) across versions, and can diff the frozen Classic CLI (rp-cli) against CE. Uses /.pi/agent/skills/repoprompt-tool-guidance-refresh/scripts/track-rp-version.sh to capture/diff --help and -l (tool…

w-winter/dot314 · 115 tokens

xcodebuildmcp

Build/test Xcode projects via the XcodeBuildMCP MCP server using a local CLI wrapper for pi (no MCP support). Use when the user mentions Xcode, xcodebuild, iOS builds/tests, or XcodeBuildMCP.

w-winter/dot314 · 56 tokens

open-pencil

Work with Figma .fig design files and the running OpenPencil editor — inspect structure, query nodes, analyze design tokens, export PNG/SVG/PDF/JSX, and modify designs programmatically. Use when asked to open, inspect, export, analyze, or edit .fig files, or to control the running OpenPencil app.

open-pencil/skills · 73 tokens