claude-code

claude-code is an agent for coding agents from tony/skills. It costs 0 tokens per session (2,511 once invoked), scanned A, original, MIT.

Validated with one Claude pane and one external native Claude peer.

Agent

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/tony/skills/claude-code
Clone the repo
git clone --depth 1 https://github.com/tony/skills

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 claude-code

README.md
[![agentmods](https://agentmods.dev/badge/agents/tony/skills/claude-code.svg)](https://agentmods.dev/agents/tony/skills/claude-code)
Your own site
<a href="https://agentmods.dev/agents/tony/skills/claude-code"><img src="https://agentmods.dev/badge/agents/tony/skills/claude-code.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 2,511 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.02511
Opus 5 $0.00000 $0.01256
Sonnet 5 $0.00000 $0.00502
Haiku 4.5 $0.00000 $0.00251

Measured today against content hash c0aa8c20bbc6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-code 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.

plugins/agent-messaging/references/agents/claude-code.md · 225 lines

How it starts

The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adapter: Claude Code 2.1.239

Validated with one Claude pane and one external native Claude peer.

Upstream: cross-session messaging.

1. Identity

  • Own address: native peers address the session by name; the local inbox address is the uds: socket URI.
  • Where exposed: /status, ListAgents, $CLAUDE_CODE_MESSAGING_SOCKET, and the live session registry.
  • Stability: the observed name and socket stayed stable. Rename, resume, restart, and collision behavior are UNKNOWN empirically.
  • Human-readable name: C used commit these changes (Branch 2); O used codex-66.

Evidence: Phase 1 in role C's findings and T3.2.

2. Discovery

  • Enumerate peers: the model-facing ListAgents tool.
  • Scope: Claude sessions only; it did not list either live Codex pane.
  • What a listing shows: name, short identifier, kind, status, and tmux coordinate when known.
  • Foreign discovery: claude agents --json lists live sessions with name, pid, and status; read the inbox from ${CLAUDE_CONFIG_DIR:-$HOME/.claude}/sessions/<pid>.json, field messagingSocketPath, rather than assuming a directory. The socket directory alone is not enough — it publishes no names, seven of twelve observed sockets were stale, and one logical session owned two.

Evidence: T1.C-disc and T1.O-disc.

3. Transports

claude-code-message (send and receive)

The model calls SendMessage with a ListAgents name. The native receiver gets a structured <cross-session-message> wrapper with sender socket, name, and permission class.

  • Preconditions: live compatible Claude sessions and the cross-session feature enabled.
  • Success signal: the tool returns a message ID; the receiver starts a turn if idle or receives it at a tool boundary if busy.
  • Failure modes: feature, provider, and version gates were not varied and remain UNKNOWN empirically.

Evidence: T3.2 and T3.2-recv.

Read the full file on GitHub · 225 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 · 225 lines · 0 tokens per session scan A c0aa8c20bbc6

Subscribe to this mod's changes

claude-code is an agent published in the GitHub repository tony/skills (2 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,511 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 2026-09-03.