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 agents/tony/skills/claude-codegit clone --depth 1 https://github.com/tony/skillsWrote 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.
[](https://agentmods.dev/agents/tony/skills/claude-code)<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>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.02511 |
| Opus 5 | $0.00000 | $0.01256 |
| Sonnet 5 | $0.00000 | $0.00502 |
| Haiku 4.5 | $0.00000 | $0.00251 |
Grade A, and why
claude-code scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adapter: Claude Code 2.1.239
Validated with one Claude pane and one external native Claude peer.
Upstream: cross-session messaging.
1. Identity
- Own address: native peers address the session by name; the local inbox address is the
uds:socket URI. - Where exposed:
/status,ListAgents,$CLAUDE_CODE_MESSAGING_SOCKET, and the live session registry. - Stability: the observed name and socket stayed stable. Rename, resume, restart, and
collision behavior are
UNKNOWNempirically. - Human-readable name: C used
commit these changes (Branch 2); O usedcodex-66.
Evidence: Phase 1 in role C's findings and T3.2.
2. Discovery
- Enumerate peers: the model-facing
ListAgentstool. - 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 --jsonlists live sessions with name, pid, and status; read the inbox from${CLAUDE_CONFIG_DIR:-$HOME/.claude}/sessions/<pid>.json, fieldmessagingSocketPath, 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
UNKNOWNempirically.
Evidence: T3.2 and T3.2-recv.
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.
- today First seen · 225 lines · 0 tokens per session scan A c0aa8c20bbc6
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.
Other agents, from other repositories
dataroom-watcher
Monitors the VDR for new document uploads and posts closing checklist status on schedule. Flags new uploads that match high-priority categories. Trigger: "what's new in the data room", "VDR updates", or on schedule.
maid-manifest-architect
MAID Phase 1 - Create and validate manifest from user's goal.
maid-test-designer
MAID Phase 2 - Create behavioral tests that USE artifacts from manifest.
maid-auditor
MAID Compliance Auditor - Enforce methodology compliance across all phases.
stakeholder-researcher
Research one stakeholder from the public record when no LinkedIn PDF is available, for a high-stakes meeting brief. Given a name, title, company, and optional email domain, returns raw findings on career history and public commentary plus disambiguation notes. Used by the job-interview-meeting-preparation skill on the…
launch-watcher
Monitors the launch tracker (Jira/Linear) for upcoming launches that likely need UK legal review, flags them before product counsel gets surprised. Runs daily. Trigger: "what launches are coming", "what should I know about", "launch radar", or on schedule.