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 commands/punt-labs/beadle/contactsgit clone --depth 1 https://github.com/punt-labs/beadleWrote 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/commands/punt-labs/beadle/contacts)<a href="https://agentmods.dev/commands/punt-labs/beadle/contacts"><img src="https://agentmods.dev/badge/commands/punt-labs/beadle/contacts.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 | $0.00004 | $0.00488 |
| Opus 5 | $0.00002 | $0.00244 |
| Sonnet 5 | $0.00001 | $0.00098 |
| Haiku 4.5 | $0.00000 | $0.00049 |
Grade A, and why
contacts 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.
What it actually says
Input
Arguments: $ARGUMENTS
Task
Manage the beadle address book. Contacts enable name-based addressing —
/mail alice resolves to the stored email without an extra lookup.
Argument routing
listor no argument — list all contactsadd— add a new contact (prompt for name and email)remove <name>— remove a contact by namefind <query>— search by name, alias, or email
List (default)
Call list_contacts. Display results as a compact table: name, email, aliases.
If empty, say "No contacts. Use /contacts add to add one."
Add
If arguments include name, email, and optionally permissions after add
(e.g., /contacts add Alice [email protected] rw-), use them directly.
Otherwise prompt for:
- Name (required, unique)
- Email (required — may be a glob pattern like
*@github.comfor domain-wider--or---only) - Permissions (optional, default
---; format:rwx,rw-,r--,---) - Aliases (optional, comma-separated)
- GPG key ID (optional)
Call add_contact with the collected fields.
Remove
Extract the name from arguments after remove.
Call remove_contact with the name. Confirm removal.
Find
Extract the query from arguments after find.
Call find_contact with the query. Display matches as a compact table.
If no matches, say "No contacts matching <query>."
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.
- 4d ago First seen · 53 lines · 4 tokens per session scan A cc577b834739
contacts is a command published in the GitHub repository punt-labs/beadle (3 stars, last pushed 4d ago), licensed MIT. It adds 4 tokens to every session and 488 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
meeting-listen
Play back a completed meeting summary as a voiced debate between personas.
meeting-hive
Run an autonomous PR/FAQ review meeting where four personas debate and reach consensus without user intervention.
vote
Assess whether a PR/FAQ should move forward with a structured go/no-go decision.
feedback
Incorporate feedback into PR/FAQ and redraft affected sections.
contracts-dev
Generate runtime contracts (preconditions, postconditions, invariants) from a Z specification.
partition-dev
Derive test cases from Z specification using TTF testing tactics.