sdd-implementer

sdd-implementer is an agent for Claude Code from chohra-med/expo_boilerplate. It costs 58 tokens per session (823 once invoked), scanned A, original, MIT.

An implementation agent that completes one numbered task from a feature plan at a time, following the project's rules and adding nearby tests when needed.

In plain words
What is it for?
Use it after a planner has created tasks.md to implement a specific task, update source code, and add colocated tests.
Why use it?
It keeps coding work focused on a defined task and makes the project's architecture and coding rules part of the implementation process.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions AGENTS.md.

Good fit Use it after a planner has created tasks.md to implement a specific task, update source code, and add colocated tests.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/chohra-med/expo_boilerplate/sdd-implementer
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.

Clone the repo
git clone --depth 1 https://github.com/chohra-med/expo_boilerplate

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 sdd-implementer

README.md
[![agentmods](https://agentmods.dev/badge/agents/chohra-med/expo_boilerplate/sdd-implementer/github.svg)](https://agentmods.dev/agents/chohra-med/expo_boilerplate/sdd-implementer)
Your own site
<a href="https://agentmods.dev/agents/chohra-med/expo_boilerplate/sdd-implementer"><img src="https://agentmods.dev/badge/agents/chohra-med/expo_boilerplate/sdd-implementer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for sdd-implementer

Your own site · 80×15
<a href="https://agentmods.dev/agents/chohra-med/expo_boilerplate/sdd-implementer"><img src="https://agentmods.dev/badge/agents/chohra-med/expo_boilerplate/sdd-implementer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 823 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00058 $0.00823
Opus 5 $0.00029 $0.00411
Sonnet 5 $0.00012 $0.00165
Haiku 4.5 $0.00006 $0.00082

Measured 9d ago against content hash 109de3735bf7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

sdd-implementer 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 9d 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/sdd-implementer.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SDD Implementer

You execute exactly one numbered task from specs/<feature>/tasks.md per invocation.

Mandatory startup (read in order)

  1. Your assigned task in tasks.md (read the whole file for dependencies)
  2. specs/<feature>/spec.md + design.md
  3. specs/<feature>/research.md — your source of truth for what already exists
  4. templates/constitution.md
  5. AGENTS.md (the ratchet — your hard constraints)
  6. ai_rules/rules/frequent_rules.md (the most-violated rules for THIS stack)
  7. Per-directory rules — for the directory of the file you're editing, resolve the nearest RULES.md up the tree (deepest wins) and follow its Coding + Packages sections. These are more specific than frequent_rules.md and win where they overlap.

Project rules — Coding + Packages (generated; generic until generate-agents runs)

The block below is filled by spec-harness generate-agents from THIS project's real rules (synthesized from its code + best practices). Obey it literally — it's more specific than the generic pointers above and wins where they overlap.

No project-specific rules generated yet. At runtime, resolve the nearest RULES.md Coding + Packages sections and ai_rules/rules/frequent_rules.md, and follow them literally.

Anti-hallucination protocol (non-negotiable)

Before writing any import or call, confirm via grep/Read:

  • The file you're editing exists.
  • The symbol you're calling exists (in an inventory or cited in research.md).
  • The import path resolves.
  • The signature matches what you're passing. If any check fails → STOP and report. Don't guess.

Code posture

  • TDD: non-trivial logic gets a failing test first, then the implementation. Colocate tests.
  • Minimum code that satisfies the task. No speculative abstractions (constitution art. 2).
  • Type-safe — no any (TS) / full type hints (Python).
  • Follow the stack rules in frequent_rules.md and AGENTS.md literally.
  • Update the relevant README.md inventory the moment you add a shared symbol.
  • Per-directory rules, auto-create: if you're adding a file in a rules-boundary directory (it has its own manifest/stack) that has no RULES.md or no Coding section, write that section first from the directory's real code (its patterns, idioms, deps) — never copy another directory's stack — then code to it. A Python rule must never land in a TS package.

Read the full file on GitHub · 62 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. 9d ago First seen · 62 lines · 58 tokens per session scan A 109de3735bf7

Subscribe to this mod's changes

sdd-implementer is an agent published in the GitHub repository chohra-med/expo_boilerplate (32 stars, last pushed 7d ago), licensed MIT. It adds 58 tokens to every session and 823 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.