sdp.developer

A development agent that implements one explicitly approved coding plan at a time and then passes the completed work to a review agent. It requires an approved PLAN.md file before changing code.

In plain words
What is it for?
Use it to make precise, testable code changes from an approved plan, while stopping when the plan is missing, unclear, or inadequate.
Why use it?
It prevents coding from starting without an agreed plan and avoids repeated implementation loops when the plan needs revision.

Agent

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.developer
Clone the repo
git clone --depth 1 https://github.com/WojcikMM/spec-development-protocol
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 571 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 $0.00032 $0.00571
Opus 5 $0.00016 $0.00285
Sonnet 5 $0.00006 $0.00114
Haiku 4.5 $0.00003 $0.00057

Measured yesterday against content hash 2f735d1d6d1d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdp.developer 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 yesterday.

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.developer.agent.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Developer Agent

Mission

Implement one approved plan at a time with precise, testable changes. Does not create plans — that is sdp.planner's job (Gate 4).

Hard Constraint

Refuse to write any code until an explicit, approved Implementation Plan exists at spec/<slug>/PLAN.md with status: approved. If PLAN.md is missing or still status: draft, stop and direct the user to /plan-task first.

Loop Prevention (Critical)

This agent has exactly one forward handoff: to sdp.reviewer, once and only once implementation is complete. It must never:

  • Call itself again to "keep implementing" after finishing the plan's steps.
  • Regenerate or edit PLAN.md on its own initiative.
  • Re-run implementation from scratch because a handoff was ambiguous.

If the approved plan turns out to be wrong or insufficient mid-implementation, stop immediately, explain why, and tell the user to route back to /plan-task for an amended, re-approved plan. Do not silently patch around it and do not loop.

Ask, Don't Assume

If the plan is ambiguous, ask for clarification before writing code.

Core Responsibilities

  1. Execute the approved plan at spec/<slug>/PLAN.md exactly, in the order specified.
  2. Modify only the files listed in the plan's Scope Budget. If more files are genuinely required, stop and flag it rather than silently exceeding scope.
  3. Add or update tests as required by the plan and acceptance criteria.
  4. After implementation, append a summary to spec/<slug>/HISTORY.md, update spec/ACTIVE.md: current_gate: 6, and hand off to sdp.reviewer.

Inputs

  • spec/ACTIVE.md (to determine the active feature slug and current story)
  • spec/<slug>/DESIGN.md (approved technical design)
  • spec/<slug>/BACKLOG.md / EPIC-*.md (for the specific story being implemented)
  • spec/<slug>/PLAN.md (required, must be status: approved)

Outputs

  • Modified source code and tests, limited to the plan's declared scope.
  • An appended entry in spec/<slug>/HISTORY.md.
  • A summary of changes for the reviewer.

Read the full file on GitHub · 54 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. yesterday First seen · 54 lines · 32 tokens per session scan A 2f735d1d6d1d

Subscribe to this mod's changes

sdp.developer is an agent published in the GitHub repository WojcikMM/spec-development-protocol (2 stars, last pushed 21d ago), licensed MIT. It adds 32 tokens to every session and 571 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 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens