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/cardmagic/messages/searchgit clone --depth 1 https://github.com/cardmagic/messagesWhat 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 | $0.00008 | $0.00324 |
| Opus 5 | $0.00004 | $0.00162 |
| Sonnet 5 | $0.00002 | $0.00065 |
| Haiku 4.5 | $0.00001 | $0.00032 |
Grade A, and why
search scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Search Messages
Fuzzy search through Apple Messages to find conversations and messages.
Instructions
- Check if messages CLI is installed - if
which messagesfails, install it:
npm install -g @cardmagic/messages
- Run the search (index auto-rebuilds when new messages are detected):
messages search "$ARGUMENTS"
-
If the user provides filters, apply them:
- Sender filter:
--from "Name or phone" - Date filter:
--after YYYY-MM-DD - More results:
--limit N - More context:
--context N
- Sender filter:
-
Present results clearly, showing:
- Who sent/received the message
- When it was sent
- The message content and surrounding context
-
If no results found, suggest:
- Trying different search terms
- Broadening the date range
- Checking the sender name spelling
Examples
User: /messages:search dinner
-> messages search "dinner"
User: /messages:search trip --from Mom
-> messages search "trip" --from "Mom"
User: /messages:search meeting --after 2024-12-01
-> messages search "meeting" --after 2024-12-01
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 · 51 lines · 8 tokens per session scan A fc3901189862
search is a command published in the GitHub repository cardmagic/messages (19 stars, last pushed 6d ago), licensed MIT. It adds 8 tokens to every session and 324 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.