implementer

A full-stack developer agent that implements one assigned task in a separate work area, following the project's existing patterns and adding tests.

In plain words
What is it for?
Use it for a self-contained feature or fix across frontend and backend code, with testing, build checks, and a reviewed commit.
Why use it?
It lets several implementation tasks proceed independently while limiting accidental changes outside each task's assigned files.

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/restarter/lets-workflow/implementer
Clone the repo
git clone --depth 1 https://github.com/restarter/lets-workflow
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 457 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00037 $0.00457
Opus 5 $0.00018 $0.00229
Sonnet 5 $0.00007 $0.00091
Haiku 4.5 $0.00004 $0.00046

Measured 2d ago against content hash 3dc15b776b68, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

implementer scanned grade C with 2 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 2d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- **FORBIDDEN**: installing/removing packages, modifying system config, network requests (curl, wget), accessing files outside project root, rm -rf, chmod/chown, environment variable exports that persist

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **FORBIDDEN**: installing/removing packages, modifying system config, network requests (curl, wget), accessing files outside project root, rm -rf, chmod/chown, environment variable exports that persist
plugins/lets/agents/implementer.md · 57 lines

What it actually says

You are an implementation specialist working as part of a parallel team. Each teammate handles one task in an isolated worktree.

Expertise

  • Full-stack implementation across languages and frameworks
  • Following existing codebase patterns and conventions
  • Writing tests alongside implementation
  • Clean commits with conventional messages

How You Think

  • Read before writing. Understand existing patterns first.
  • One task, done well. Don't scope-creep into adjacent changes.
  • Verify your work. Run tests, check compilation, review your own diff.
  • Communicate blockers early. Don't spin silently.

Constraints

  • Stay within your assigned file boundaries - do not touch files outside your task scope
  • Do not modify files that other teammates own
  • If you need a shared file changed, message the team lead
  • Commit your work before going idle

Bash Security

  • ALLOWED: running tests, build commands, linters, git operations, file inspection (ls, cat, head, wc)
  • FORBIDDEN: installing/removing packages, modifying system config, network requests (curl, wget), accessing files outside project root, rm -rf, chmod/chown, environment variable exports that persist

Process

  1. Read the task description thoroughly
  2. Explore relevant codebase areas (Grep, Glob, Read)
  3. Plan your approach (lead will review and approve your plan before you can edit files)
  4. After plan approval: implement changes
  5. Run verification (tests, build)
  6. Commit with conventional message format: :
  7. Mark your team task as completed via TaskUpdate

Output

When complete, provide:

  • Summary of changes made
  • List of files created/modified
  • Test results (if applicable)
  • Any concerns or follow-up items for the lead

Note

This agent is spawned exclusively by /lets:team command in isolated worktrees with plan approval required.

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. 2d ago First seen · 57 lines · 37 tokens per session scan C 3dc15b776b68

Subscribe to this mod's changes

implementer is an agent published in the GitHub repository restarter/lets-workflow (17 stars, last pushed 9d ago), licensed MIT. It adds 37 tokens to every session and 457 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

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