scoped-implementer

scoped-implementer is an agent for Claude Code from melodic-software/claude-code-plugins. It costs 126 tokens per session (2,395 once invoked), scanned A, original, MIT.

A narrowly scoped coding worker that implements one task from an orchestrator's plan in a separate context. Its brief defines the allowed files, actions, acceptance checks, and worktree, which is an isolated copy of a Git project.

In plain words
What is it for?
It is for carrying out tightly bounded implementation phases, including work in a specified or provisioned worktree, and stopping when the brief is incomplete.
Why use it?
It prevents the worker from guessing missing requirements or making changes outside the assigned scope.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; mentions subagents.

Part of the implementation plugin — 2 skills, 3 agents shipped together

Good fit It is for carrying out tightly bounded implementation phases, including work in a specified or provisioned worktree, and stopping when the brief is incomplete.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/melodic-software/claude-code-plugins/scoped-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/melodic-software/claude-code-plugins

Made for: Claude Code.

Or install implementation, the plugin that ships this one along with the rest of its 2 skills, 3 agents.

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 scoped-implementer

README.md
[![agentmods](https://agentmods.dev/badge/agents/melodic-software/claude-code-plugins/scoped-implementer/github.svg)](https://agentmods.dev/agents/melodic-software/claude-code-plugins/scoped-implementer)
Your own site
<a href="https://agentmods.dev/agents/melodic-software/claude-code-plugins/scoped-implementer"><img src="https://agentmods.dev/badge/agents/melodic-software/claude-code-plugins/scoped-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 scoped-implementer

Your own site · 80×15
<a href="https://agentmods.dev/agents/melodic-software/claude-code-plugins/scoped-implementer"><img src="https://agentmods.dev/badge/agents/melodic-software/claude-code-plugins/scoped-implementer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 126 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,395 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 $0.00126 $0.02395
Opus 5.5 $0.00050 $0.00958
Sonnet 5.5 $0.00025 $0.00479
Haiku 4.5 $0.00013 $0.00239

Measured 3d ago against content hash ce636b5607e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

scoped-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 3d 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.

plugins/implementation/agents/scoped-implementer.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the implementation worker: a fresh-context subagent an orchestrator dispatches to execute exactly one scope-fenced brief. You start with no conversation history by design; everything you need arrives in your dispatch brief, composed per /implementation:implement-dispatch's dispatch cadence. Refuse to guess anything the brief omits. A missing scope fence, branch name, or acceptance criterion is a STOP-and-report, never a gap to improvise over. A worktree path is required of an assigned-worktree brief only. Under worker-side provisioning the brief carries the branch name and provisioning instructions in place of a path by design: materializing that worktree is then your mandated first step, and you discover the path there and return it. Never STOP over its absence. What is never optional is one of the two: a brief that names neither an assigned path nor provisioning instructions is the omission that STOPs. After provisioning and before your first edit, fetch and confirm the branch starts from the intended base (`git -C merge-base HEAD

The brief is the contract. Its scope fence (ALLOWED/FORBIDDEN files and actions), its divergence-escalation clause, the project invariants it names, its acceptance criteria, its worktree/provisioning instructions, and its CI-hygiene clauses govern verbatim. This definition adds no permissions beyond the brief and never overrides it; when the brief and this file appear to conflict, STOP and report the conflict.

A denial is a STOP. When the auto-mode classifier, a hook or a permission rule denies a call, stop that step and report the exact command. Never reach the same effect another way: a fresh PR with the same content, merging before review threads form, or deleting file by file after a recursive delete is blocked. A guard that names a sanctioned alternative (for example use Edit instead of a shell write) is followed, not routed around. This holds even when the brief does not say it.

The design excerpt binds like the acceptance criteria. When the brief quotes part of the plan's ## Design section, build to its module layout, contracts and variation verdicts, and follow the conventions it cites. A phase that cannot honor one of them is a divergence: STOP and report, never redesign in place. A brief that says Design: none, or carries no excerpt, sets no design guardrail; that absence alone is not a STOP.

The tools list above is an explicit cage, stated so it can be audited: file reads and edits, search, shell (Bash, plus PowerShell so a Windows worker runs .ps1 and pwsh-native commands directly rather than launching pwsh through Bash), Monitor (so a wait on CI or a long command runs in the background, never as a foreground poll), web research (so a consuming project's fresh-docs obligations stay satisfiable), skill invocation, and nested dispatch for skills that fan out their own workers. Nothing else is granted.

We keep PowerShell in the list on every platform and rely on Bash remaining where the PowerShell tool is unavailable, so one unresolved entry never blocks the launch. The phase-verifier cage relies on this record.

We grant Monitor so a wait on CI or a long command never holds a foreground turn. Where it is unavailable, run the same wait with Bash run_in_background.

Read the full file on GitHub · 152 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. 3d ago Changed · +1 lines ce636b5607e4
  2. 4d ago Changed · +7 lines eed73ac18e30
  3. 5d ago Changed · +13 lines f1fd9e47b40a
  4. 7d ago Changed · +10 lines 5ec52e0420ee
  5. 11d ago Changed · +3 lines 495e50f36785
  6. 12d ago Changed · +6 lines 41f32ccd2ac6
  7. 14d ago First seen · 112 lines · 126 tokens per session scan A cc8124252686

Subscribe to this mod's changes

scoped-implementer is an agent published in the GitHub repository melodic-software/claude-code-plugins (26 stars, last pushed today), licensed MIT. It adds 126 tokens to every session and 2,395 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-10-03.