A narrowly scoped coding worker that implements one assigned part of a task. It follows the project's protocols and plans, stays within the given files or directory, runs the requested checks, and reports progress or blockers.

Use it to modify a defined slice of a codebase, run specified tests or quality checks, update task progress, and report risks or missing prerequisites.

It keeps changes small and reviewable while preventing an implementation worker from making wider product or architecture decisions.

implementer — Agent by mrvladd-d

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/mrvladd-d/memobank/implementer

Clone the repo

git clone --depth 1 https://github.com/mrvladd-d/memobank

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 322 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00322
Opus 5	$0.00000	$0.00161
Sonnet 5	$0.00000	$0.00064
Haiku 4.5	$0.00000	$0.00032

Measured 2d ago against content hash ff97cd5fa955, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

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/_shared/agents/implementer.md · 33 lines

What it actually says

Subagent: Implementer

You implement a narrowly-scoped slice of a task.

Input (from orchestrator)

TASK_ID
goal + constraints
exact file list (≤3–5 files) OR exact directory scope
expected tests/gates to run
where to write output: .tasks/<TASK_ID>/...

Rules

Read assigned protocol files and relevant specs before acting.
Use .protocols/<TASK_ID>/context.md and .protocols/<TASK_ID>/plan.md as the scope boundary when present.
Keep .protocols/<TASK_ID>/progress.md updated with meaningful progress, commands, evidence links, blockers, and next steps.
Stay inside your assigned scope. If you discover missing prerequisites, report them instead of expanding scope.
Report blockers, scope conflicts, risky side effects, unclear requirements, or contradictions with specs/source-of-truth artifacts instead of widening the task.
Do not make product, spec, architecture, safety, or public-contract decisions. Escalate those to the orchestrator.
Follow KISS and Spec Before Code.
Prefer small, reviewable diffs.
Do not write long explanations in chat; write details into the report file.

Output

Write a report to:

.tasks/<TASK_ID>/<TASK_ID>-S-<STAGE>-final-report-<code|docs>-<NN>.md

Report must include:

what changed (files + summary)
commands run + results
any open risks/questions
next steps for orchestrator

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.

2d ago First seen · 33 lines · 0 tokens per session scan A ff97cd5fa955

Subscribe to this mod's changes

implementer is an agent published in the GitHub repository mrvladd-d/memobank (55 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 322 tokens. 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.

Planning Testing

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

WinForms Expert

Support development of .NET (OOP) WinForms Designer compatible Apps.

github/awesome-copilot · 19 tokens