claude-marketplace: Agent for Claude Code

.claude/agents/sonnet-implementer.md

sonnet-implementer is an agent for Claude Code from davistroy/claude-marketplace. It costs 66 tokens per session (514 once invoked), scanned A, original, MIT.

A software-development agent for well-defined engineering work, including tests, small refactors, documentation, bug fixes, code reviews, and clearly specified features. A refactor changes code structure without changing its intended behavior.

In plain words
What is it for?
Use it to write tests, update documentation, fix known bugs, review code, or implement a feature with explicit acceptance criteria.
Why use it?
It handles routine implementation when the requirements are clear and signals when a task needs broader architectural decisions or a large coordinated change.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is davistroy/claude-marketplace's own configuration. It tells Claude Code how to work on claude-marketplace itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-marketplace configures →

Reuse

Borrowing it

Nothing to install: this file belongs to davistroy/claude-marketplace. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/davistroy/claude-marketplace/main/.claude/agents/sonnet-implementer.md
Clone the repo
git clone --depth 1 https://github.com/davistroy/claude-marketplace

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 sonnet-implementer

README.md
[![agentmods](https://agentmods.dev/badge/agents/davistroy/claude-marketplace/sonnet-implementer.svg)](https://agentmods.dev/agents/davistroy/claude-marketplace/sonnet-implementer)
Your own site
<a href="https://agentmods.dev/agents/davistroy/claude-marketplace/sonnet-implementer"><img src="https://agentmods.dev/badge/agents/davistroy/claude-marketplace/sonnet-implementer.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 514 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 $0.00066 $0.00514
Opus 5 $0.00033 $0.00257
Sonnet 5 $0.00013 $0.00103
Haiku 4.5 $0.00007 $0.00051

Measured 8d ago against content hash cee383c88394, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

sonnet-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 8d 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/sonnet-implementer.md · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a skilled implementation agent for standard software engineering work. Your task is well-scoped: the plan provides clear acceptance criteria and you have enough context to complete the work correctly without major judgment calls.

Your Task Profile

You handle:

  • Tests against a spec — write unit or integration tests for clearly described behavior
  • Single-file refactors — restructure, extract, or simplify code within a bounded file scope
  • Documentation updates — write or revise docs, docstrings, READMEs, changelogs
  • Straightforward bug fixes — diagnose and fix clearly-identified bugs with known root causes
  • Code review — assess code against a rubric and produce structured findings
  • New features with clear specs — implement features where the API surface and behavior are fully described

Execution Rules

  1. Read the plan first. The work item in IMPLEMENTATION_PLAN.md is your spec. Follow the Tasks and Acceptance Criteria exactly.
  2. Complete ALL tasks listed in the work item's Tasks section.
  3. Update the plan. When done, change **Status: PENDING** to **Status: COMPLETE [YYYY-MM-DD]** and decorate the heading with ✅ Completed YYYY-MM-DD.
  4. Update Risk Mitigation. If the plan's Risk Mitigation table has risks related to this work item, update their Status from Open to Mitigated.
  5. Return minimal output: (1) files created/modified, (2) implementation summary (max 3 sentences), (3) DONE.

Escalation

If you discover mid-execution that the task requires:

  • Architectural choices between competing designs not resolved by the spec
  • Multi-file refactoring with system-wide coupling not anticipated in the plan
  • Requirements that are genuinely ambiguous and cannot be resolved from available context
  • Cross-cutting debugging where the root cause spans multiple subsystems

Return ESCALATE: [clear one-sentence reason] immediately — do not guess or partially implement. The orchestrator will re-dispatch at a higher tier (Opus).

Read the full file on GitHub · 36 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. 8d ago First seen · 36 lines · 66 tokens per session scan A cee383c88394

Subscribe to this mod's changes

sonnet-implementer is an agent published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 514 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 2026-08-31.

Related

Other agents, from other repositories

pr-test-analyzer

Use this agent when you need to review a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or updated to ensure tests adequately cover new functionality and edge cases. Examples:\n\n \nContext: Daisy has just created a pull request with new…

anthropics/claude-code · 0 tokens

ai-hygiene-auditor

Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.

athola/claude-night-market · 48 tokens

sap-test-plan-reviewer

Adversarial review of a test-case plan produced by design-cases. READS the actual ABAP source snapshot (plus findings.md, flow.md, units.md, and the TC-.md files) to catch branches and MESSAGEs the plan missed, checks total case count against the enumerated minimum, checks every mandatory category has at least one…

marcellourbani/vscode_abap_remote_fs · 161 tokens

edge-case-explorer

Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…

testdouble/han · 135 tokens

sdd-init

Initialize project SDD context, testing capabilities, and skill registry.

Gentleman-Programming/gentle-pi · 17 tokens

test-reviewer

Reviews test coverage and test quality for code changes.

ai-sdlc-framework/ai-sdlc · 13 tokens