implement.body

implement.body is a command for Claude Code from sergeyklay/.agents. It costs 0 tokens per session (216 once invoked), scanned A, original, Apache-2.0.

A command template for sending work to another agent, such as an implementation agent or a testing agent. It chooses the appropriate kind of helper for the task.

In plain words
What is it for?
Use it when a coding task should be handed to a separate implementation, testing, or project-specific specialist agent.
Why use it?
It keeps delegated work using the correct agent type and avoids confusing delegation with a task checklist.

Command 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 commands/sergeyklay/.agents/implement.body
Clone the repo
git clone --depth 1 https://github.com/sergeyklay/.agents

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 implement.body

README.md
[![agentmods](https://agentmods.dev/badge/commands/sergeyklay/.agents/implement.body.svg)](https://agentmods.dev/commands/sergeyklay/.agents/implement.body)
Your own site
<a href="https://agentmods.dev/commands/sergeyklay/.agents/implement.body"><img src="https://agentmods.dev/badge/commands/sergeyklay/.agents/implement.body.svg" alt="Measured on agentmods" height="20"></a>
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 216 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 $0.00000 $0.00216
Opus 5 $0.00000 $0.00108
Sonnet 5 $0.00000 $0.00043
Haiku 4.5 $0.00000 $0.00022

Measured 4d ago against content hash 3635be4d5bf0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implement.body 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 4d 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.

templates/.claude/commands/implement.body.md · 11 lines

What it actually says

Delegation primitive

Every subagent invocation uses the delegation tool with the appropriate subagent_type (the implementation subagent, the tester subagent, or any specialized subagent the project ships). That tool is named Agent in an interactive Claude Code session and Task in the headless runtime (claude -p, Agent SDK). Read your toolbox and call whichever of the two is actually present; do not assume a particular name and do not conclude the other one is missing. The task-list tools TaskCreate / TaskUpdate / TaskGet / TaskList are a separate todo mechanism, not delegation, and were previously called TodoWrite.

Omit the name parameter on every delegation call: pass subagent_type and the prompt only. These subagents never message each other, so a name buys nothing, and with agent teams enabled a named spawn is registered as a team member - which cannot spawn further agents and fails this pipeline at its next delegation.

Implementation Request

$ARGUMENTS

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. 4d ago First seen · 11 lines · 0 tokens per session scan A 3635be4d5bf0

Subscribe to this mod's changes

implement.body is a command published in the GitHub repository sergeyklay/.agents (5 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 216 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 2026-08-31.