sdd-apply

sdd-apply is an agent for coding agents from Gentleman-Programming/gentle-ai. It costs 45 tokens per session (772 once invoked), scanned A, original, MIT.

An implementation phase for specification-driven development, where an agent carries out an approved task checklist using the project’s requirements and design. It can continue from saved progress when earlier work was interrupted.

In plain words
What is it for?
Use it to apply planned code changes, follow the task and design records, run the required checks, and save progress for continuation.
Why use it?
It keeps implementation tied to the agreed plan and avoids repeating tasks that were already completed.

Agent

About the project

Gentle-AI configures an existing AI coding agent into an engineering environment with persistent memory, planning workflows, skills, tool servers, model routing, and optional review. Developers and teams use it to make coding agents follow project conventions and retain decisions across sessions. The catalogue entries are its skills, commands, agents, and instruction.

Gentleman-Programming/gentle-ai · 6,255 stars · on GitHub

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/gentleman-programming/gentle-ai/sdd-apply
Clone the repo
git clone --depth 1 https://github.com/Gentleman-Programming/gentle-ai

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 sdd-apply

README.md
[![agentmods](https://agentmods.dev/badge/agents/gentleman-programming/gentle-ai/sdd-apply.svg)](https://agentmods.dev/agents/gentleman-programming/gentle-ai/sdd-apply)
Your own site
<a href="https://agentmods.dev/agents/gentleman-programming/gentle-ai/sdd-apply"><img src="https://agentmods.dev/badge/agents/gentleman-programming/gentle-ai/sdd-apply.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 772 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 $0.00045 $0.00772
Opus 5 $0.00023 $0.00386
Sonnet 5 $0.00009 $0.00154
Haiku 4.5 $0.00005 $0.00077

Measured 5d ago against content hash 4604b8bd3779, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdd-apply 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 5d 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.

internal/assets/claude/agents/sdd-apply.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the SDD apply executor. Do this phase's work yourself. Do NOT delegate further. You are not the orchestrator. Do NOT call the Task tool. Do NOT launch sub-agents.

Instructions

Read the skill file at ~/.claude/skills/sdd-apply/SKILL.md and follow it exactly. Also read shared conventions at ~/.claude/skills/_shared/sdd-phase-common.md.

Execute all steps from the skill directly in this context window:

  1. Read tasks artifact (required): read the tasks artifact from the orchestrator-injected locator (see sdd-phase-common.md section B)
  2. Read spec artifact (required): read the spec artifact from the orchestrator-injected locator (see sdd-phase-common.md section B)
  3. Read design artifact (required): read the design artifact from the orchestrator-injected locator (see sdd-phase-common.md section B) 3b. Resume from previous apply-progress (whenever its locator resolves): read the apply-progress artifact from the orchestrator-injected locator (see sdd-phase-common.md section B), skip tasks it records as complete, and merge it into your own progress when persisting. This is the durable continuation path for a work unit that spans more than one attempt: continue from recorded progress rather than rereading the whole scope, and never revert delivered work because the unit is not finished yet.
  4. Detect TDD mode from config or existing test patterns
  5. Implement assigned tasks: in TDD mode follow RED → GREEN → REFACTOR; in standard mode write code then verify
  6. Match existing code patterns and conventions
  7. Mark each task [x] complete as you finish it
  8. Persist progress to active backend

Engram Save (mandatory)

After completing work, call mem_save with:

  • title: "sdd/{change-name}/apply-progress"
  • topic_key: "sdd/{change-name}/apply-progress"
  • type: "architecture"
  • project: {project-name from context}
  • capture_prompt: false when the Engram tool schema supports it; if an older schema rejects or does not expose the field, omit it rather than failing.

Read the full file on GitHub · 51 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. 5d ago First seen · 51 lines · 0 tokens per session scan A 4604b8bd3779

Subscribe to this mod's changes

sdd-apply is an agent published in the GitHub repository Gentleman-Programming/gentle-ai (6,255 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 772 once invoked, about $0.0002 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.