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/bradduy/wiki-knowledge-compiler/wiki-schedulegit clone --depth 1 https://github.com/bradduy/wiki-knowledge-compilerWrote 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/bradduy/wiki-knowledge-compiler/wiki-schedule)<a href="https://agentmods.dev/commands/bradduy/wiki-knowledge-compiler/wiki-schedule"><img src="https://agentmods.dev/badge/commands/bradduy/wiki-knowledge-compiler/wiki-schedule.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 | $0.00019 | $0.01468 |
| Opus 5 | $0.00010 | $0.00734 |
| Sonnet 5 | $0.00004 | $0.00294 |
| Haiku 4.5 | $0.00002 | $0.00147 |
Grade A, and why
wiki-schedule 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 5d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wiki Schedule
Help the user set up automatic /wiki-update runs. This creates a remote scheduled agent that checks raw/ for new files and rebuilds indexes on a schedule.
Procedure
Step 1: Ask what kind of schedule (MUST ASK)
Present this to the user and WAIT for their answer:
How would you like to schedule /wiki-update?
1. ⏰ At a specific time every day (e.g. "every day at 9am")
2. 🔁 On a repeating interval (e.g. "every 2 hours")
3. 📅 At a specific time on certain days (e.g. "every Monday at 10am")
4. 🎯 Both — daily at a specific time AND on an interval
Enter 1-4:
Step 2: Collect schedule details based on their choice
If 1 (daily at specific time):
- Ask:
What time? (Your timezone is Asia/Saigon) - Give examples: 6am, 9am, 12pm, 6pm, 10pm
- Convert their local time to UTC: Asia/Saigon is UTC+7
- e.g. 9am Saigon = 2am UTC → cron:
0 2 * * *
- e.g. 9am Saigon = 2am UTC → cron:
- Confirm:
9:00 AM Saigon = 2:00 AM UTC. Schedule: daily at 9:00 AM your time. Correct?
If 2 (repeating interval):
- Ask:
How often? - Give options:
1. Every 1 hour 2. Every 2 hours 3. Every 4 hours 4. Every 6 hours 5. Every 12 hours - Minimum is 1 hour. If they ask for less, explain the minimum.
- Convert to cron: e.g. every 2 hours →
0 */2 * * *
If 3 (specific days):
- Ask:
Which days?(Monday-Friday, weekends, specific days) - Ask:
What time? - Convert to cron: e.g. Monday & Wednesday at 9am Saigon →
0 2 * * 1,3
If 4 (both):
- Collect both a daily time AND an interval
- This creates TWO separate schedules
- Collect daily time first, then interval
Step 3: Confirm the schedule
Show the user what will be created:
Here's what I'll set up:
📋 Name: wiki-update-daily (or wiki-update-interval, etc.)
⏰ Schedule: Every day at 9:00 AM (your time) / Every 2 hours
🔧 What it does: Checks raw/ for new files, ingests them, rebuilds indexes
🤖 Model: claude-sonnet-4-6
📂 Repo: bradduy/wiki-knowledge-compiler
Create this schedule? (yes/no)
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.
- 5d ago First seen · 159 lines · 19 tokens per session scan A de5c74fd9a14
wiki-schedule is a command published in the GitHub repository bradduy/wiki-knowledge-compiler (11 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 19 tokens to every session and 1,468 once invoked, about $0.0001 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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.