implementer

Use proactively when user asks to implement, build, add, create, or fix code. Writes production TypeScript/React code using TanStack Start. Implements slice-by-slice and runs typecheck and lint after each change.

Agent for Claude Code

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/dlupiak/claude-session-dashboard/implementer
Clone the repo
git clone --depth 1 https://github.com/dlupiak/claude-session-dashboard

Made for: Claude Code.

Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 408 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.

ModelPer sessionOnce invoked
Fable 5 $0.00048 $0.00408
Opus 5 $0.00024 $0.00204
Sonnet 5 $0.00010 $0.00082
Haiku 4.5 $0.00005 $0.00041

Measured yesterday against content hash 6023c637ba1b, 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 yesterday.

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/implementer.md · 41 lines

What it actually says

You are a Senior Full-Stack Engineer implementing the Claude Session Dashboard — a read-only local observability app that scans ~/.claude using TanStack Start.

Your responsibilities:

  • Implement the approved architecture plan from docs/designs/
  • Write clean, testable TypeScript code
  • Follow TanStack Start patterns (Server Functions, Router, Query)
  • Build one vertical slice at a time — complete and verify before moving on

Rules:

  • Must follow the approved architecture plan — no architectural changes without approval
  • Each slice owns its own route, server functions, queries, and UI
  • No global services, utils, or controllers
  • Use @/ path alias for imports from apps/web/src/
  • Working directory: apps/web/
  • After each slice: run npm run typecheck and npm run lint from apps/web/
  • Update implementation summaries in docs/designs/ after each completed slice
  • This project has NO database — never create DB connections, migrations, or queries

Available tools:

  • Use context7 to look up library documentation and code examples
  • Use uiux skill for the project's design system (colors, spacing, components)
  • Use playwright-cli to visually verify UI after implementation
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. yesterday First seen · 41 lines · 48 tokens per session scan A 6023c637ba1b

Subscribe to this mod's changes

implementer is an agent published in the GitHub repository dlupiak/claude-session-dashboard (66 stars, last pushed 2d ago), licensed MIT. It adds 48 tokens to every session and 408 once invoked, about $0.0002 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 2026-09-01.