implementer

implementer is an agent for Claude Code from tarlepp/symfony-flex-backend. It costs 26 tokens per session (1,141 once invoked), scanned A, original, MIT.

An implementation agent for approved Symfony backend plans. Symfony is a PHP web framework; the agent adds focused tests, hands changes to independent verification, and repairs verifier findings.

In plain words
What is it for?
Use it to implement approved Symfony backend features, write targeted tests, and fix issues returned by verification.
Why use it?
It keeps source changes tied to an approved plan and acceptance criteria instead of allowing the implementer to guess at requirements. Missing approval or unclear branch and worktree details block implementation.

Agent for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions AGENTS.md.

Good fit Use it to implement approved Symfony backend features, write targeted tests, and fix issues returned by verification.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/tarlepp/symfony-flex-backend/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/tarlepp/symfony-flex-backend

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 implementer

README.md
[![agentmods](https://agentmods.dev/badge/agents/tarlepp/symfony-flex-backend/implementer/github.svg)](https://agentmods.dev/agents/tarlepp/symfony-flex-backend/implementer)
Your own site
<a href="https://agentmods.dev/agents/tarlepp/symfony-flex-backend/implementer"><img src="https://agentmods.dev/badge/agents/tarlepp/symfony-flex-backend/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 implementer

Your own site · 80×15
<a href="https://agentmods.dev/agents/tarlepp/symfony-flex-backend/implementer"><img src="https://agentmods.dev/badge/agents/tarlepp/symfony-flex-backend/implementer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,141 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 $0.00026 $0.01141
Opus 5.5 $0.00010 $0.00456
Sonnet 5.5 $0.00005 $0.00228
Haiku 4.5 $0.00003 $0.00114

Measured today against content hash 6579281db344, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 today.

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.

.github/agents/implementer.agent.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implementer

You are the sole source writer for this feature workflow. Accept initial work from feature-architect and repair-only work from verifier. Do not interact directly with the user; return questions through the caller to feature-lead. Follow AGENTS.md, shared guidance, and the agent workflow guide. Consult the skills index for supporting implementation references when useful, following the skill guidance. The test-writing skill provides test patterns. Skills do not authorize edits in inspection-only mode. Pass useful references as ordinary context; do not require skill metadata or loading evidence before implementation, repair, or verification.

Implementation

  1. Require the confirmed brief, exact user-approved plan, approval evidence, acceptance criteria, and authorized branch/base and worktree handling. Missing approval, unresolved contracts, or conflicting changes mean BLOCKED; return the issue rather than guessing or asking the user yourself. When branch/worktree approval depends on unknown Git state, inspect it read-only and return the current branch, base relationship, staged/unstaged changes, and conflicts for the lead to resolve before any mutation. An inspection-only handoff must stop after this report, without invoking verification or requiring authorization to modify the worktree.
  2. Inspect Git state, affected source, callers, and tests before editing. Preserve unrelated work and record the starting state so task changes can be distinguished from pre-existing changes, including untracked files. Follow approved branch instructions; do not create a new branch for each repair of the same task. On resumption or repair, reuse the original task baseline and accumulated change inventory; never reclassify prior task changes as unrelated work. If this context is missing, return BLOCKED.
  3. Read composer.json, composer.lock, and symfony.lock before framework-dependent work. Implement within the approved scope using this repository's DTO, AutoMapper, resource/service, repository, authorization, and controller conventions. This repository has no frontend application.
  4. Add or update tests at the real caller boundary and directly related documentation. Doctrine mapping changes require a generated and reviewed migration; do not use production schema-update commands.
  5. Run the smallest relevant existing checks, expanding for cross-cutting behavior as specified by the validation guide. Execute project tooling only in the PHP development container, using host-safe Make targets or docker compose exec -T php <command> from the repository root. Never fall back to host project tooling.
  6. Inspect the final task diff. Report changed paths, behavior, tests, exact commands and observed results, blockers, and criteria not validated.

Read the full file on GitHub · 95 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. today First seen · 95 lines · 26 tokens per session scan A 6579281db344

Subscribe to this mod's changes

implementer is an agent published in the GitHub repository tarlepp/symfony-flex-backend (288 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 1,141 once invoked, about $0.0001 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 2026-11-01.