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/bro3886/rem/prep-for-taskgit clone --depth 1 https://github.com/BRO3886/remWhat 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 | $0.00496 |
| Opus 5 | $0.00000 | $0.00248 |
| Sonnet 5 | $0.00000 | $0.00099 |
| Haiku 4.5 | $0.00000 | $0.00050 |
Grade A, and why
prep-for-task 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bootstrap context for a new session on the rem project. Run this BEFORE starting any implementation work.
Instructions
Launch these exploration subagents in parallel to gain comprehensive project context:
Agent 1: Project Overview
Read these files and summarize the project state:
CLAUDE.md— architecture, non-negotiables, build/test commandsREADME.md— public API, features, limitations- Auto memory — check
~/.claude/projects/for a directory matching the current working directory (the folder name is the absolute path with/replaced by-). Readmemory/MEMORY.mdinside it for accumulated patterns and gotchas. go.mod— module name and Go version- Run
git log --oneline -20for recent commit history - Run
git statusfor working tree state
Agent 2: Codebase Structure
Explore the full directory tree and map out:
- All Go files in each package (
cmd/rem/,cmd/rem/commands/,internal/) - Test files
- go-eventkit dependency version
Agent 3: Journal History
Read journals/ — find the latest journal file and read ALL sessions. Extract:
- What has been built so far (per session)
- Key technical gotchas and failures
- Architectural decisions and their rationale
- What was deferred and why
After Exploration
Summarize your findings to the user in this format:
## Project State
- Commands implemented: <list>
- Commands remaining: <list>
- go-eventkit version: <version>
## Recent Changes
<last 5 commits, one line each>
## Key Gotchas to Remember
<top 5 technical pitfalls from journals and memory>
## Ready for Task
<confirm context is loaded, ask what to work on>
Rules
- ALWAYS read
CLAUDE.mdyourself (not via subagent) before launching any agents — it contains critical project context, hosting info, and conventions that you must internalize directly - Use subagents for ALL exploration — maximize parallelism
- Do NOT write or modify any files during prep
- Do NOT start implementation until the user gives you a task
- If a plan file exists at
~/.claude/plans/*.md, read it and mention it in your summary
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 · 55 lines · 0 tokens per session scan A cad210e16dfd
prep-for-task is a command published in the GitHub repository BRO3886/rem (151 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 496 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 2026-08-30.
Other commands, from other repositories
Manage macOS Mail.app - list, read, search, send, reply, update flags, move, delete, and verify sender authentication.
reminders
Manage macOS reminders - list, search, create, complete, update, delete with filtering and batch operations.
authorize
Check and request macOS permissions for calendars, reminders, contacts, and Mail.app automation.
calendars
Manage macOS calendar events - list, search, create, update, delete with batch operations.
configure
Configure which domains, calendars, and reminder lists the plugin can access.
contacts
Manage macOS contacts - list, search, get details, create, update, delete.