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.
npx agentmods add skills/stefan-jansen/coding-agent-toolkit/delegatenpx skills add stefan-jansen/coding-agent-toolkit --skill delegategit clone --depth 1 https://github.com/stefan-jansen/coding-agent-toolkitWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00150 | $0.01930 |
| Opus 5 | $0.00075 | $0.00965 |
| Sonnet 5 | $0.00030 | $0.00386 |
| Haiku 4.5 | $0.00015 | $0.00193 |
Grade A, and why
delegate 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
delegate — coordinate your other Claude Code sessions
Deliver a piece of text from this session to another of your Claude Code
sessions, and drive the delegate/coordinate/monitor loop that a fleet of
tmux-pane or git-worktree agents runs on. Two tools do it: ListAgents
discovers who you can reach; SendMessage delivers one plain-text message
to a peer by name (SendMessage({to: "<name>", message: "..."})).
Full reference: https://code.claude.com/docs/en/cross-session-messaging
When to use this vs. something else
Use messaging when a session that already exists and is being steered separately needs one piece of information from this one, or vice versa:
- Hand over a finding — you changed something that breaks what a peer is building on; warn that peer.
- Coordinate worktrees — tell the other worktrees what landed on the shared repo.
- Pull status — ask a long-running migration/test session to report back.
- Delegate a scoped ask — hand a peer a self-contained unit and collect its reply.
Do not reach for messaging when a purpose-built mechanism fits better:
| Need | Use instead |
|---|---|
| Continue one conversation elsewhere / share its context | resume the session (--resume, /resume) |
| A team of agents THIS session spawns and supervises | subagents (Agent tool) / agent teams |
| Push external events (CI, chat) into a session | channels |
| Steer a session yourself from another device | Remote Control |
A message carries only its text — never conversation history or files. If the peer needs your context, resume it; don't try to narrate the whole session into a message.
Preflight (once per session, when a send fails or peers look missing)
claude --version # need >= 2.1.224 (>= 2.1.232 for @-mention + /config row)
# messaging live iff the socket is bound:
[ -n "$CLAUDE_CODE_MESSAGING_SOCKET" ] && echo "messaging on" || echo "messaging OFF"
If /list-agents isn't recognized, the session predates the feature or a
feature-flag-killing env var is set (CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC,
DISABLE_TELEMETRY, DO_NOT_TRACK, DISABLE_GROWTHBOOK) — unset it and restart.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 146 lines · 150 tokens per session scan A aabfa8222fb4
delegate is a skill published in the GitHub repository stefan-jansen/coding-agent-toolkit (22 stars, last pushed 17d ago), licensed MIT. It adds 150 tokens to every session and 1,930 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
mcporter
List, auth, and call MCP servers/tools from the terminal.
agent-messaging
Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "send a message to an agent", "check agent inbox", "message another agent", "reply to a message", "notify an agent", or any inter-agent communication task.
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
agent-mode
Unified tool for managing agent LLM modes (add, remove, update, list, switch).
agento11y-prod-setup
Sets up production evaluation and guardrails for a DEPLOYED AI agent in Grafana Agent Observability, grounded in the agent's own code and its real ingested traffic. The judgment layer on top of the agento11y skill: it reads the agent's source (system prompt, tools, entrypoint) AND samples its live traffic via gcx…