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.
git clone --depth 1 https://github.com/mimurchison/claude-chief-of-staffWrote 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/mimurchison/claude-chief-of-staff/my-tasks)<a href="https://agentmods.dev/commands/mimurchison/claude-chief-of-staff/my-tasks"><img src="https://agentmods.dev/badge/commands/mimurchison/claude-chief-of-staff/my-tasks/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/mimurchison/claude-chief-of-staff/my-tasks"><img src="https://agentmods.dev/badge/commands/mimurchison/claude-chief-of-staff/my-tasks.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.01055 |
| Opus 5 | $0.00000 | $0.00528 |
| Sonnet 5 | $0.00000 | $0.00211 |
| Haiku 4.5 | $0.00000 | $0.00105 |
Grade A, and why
my-tasks 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 13d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/my-tasks — Task Management
Description
Track, prioritize, and execute tasks with goal alignment and due date awareness. Claude doesn't just remind you — it helps get work done.
Arguments
list— Show all active tasks, grouped by urgencyadd "title" --due YYYY-MM-DD --goal "goal-name"— Add a new taskcomplete <task-id>— Mark a task as completeexecute— Work on the highest-priority pending taskoverdue— Show only overdue and at-risk tasks
Task File
Location: ~/.claude/my-tasks.yaml
Instructions
/my-tasks list
Read ~/.claude/my-tasks.yaml and present tasks grouped by urgency:
TASKS
OVERDUE (action required)
- [task-id] [title] — due [date] ([X days late]) — goal: [goal]
DUE TODAY
- [task-id] [title] — goal: [goal]
APPROACHING (next 7 days)
- [task-id] [title] — due [date] ([X days]) — goal: [goal]
LATER
- [task-id] [title] — due [date] — goal: [goal]
Summary: [X] active tasks, [Y] overdue, [Z] due this week
If there are overdue tasks, flag them prominently and ask: "Want me to help execute [task], reschedule it, or break it down?"
/my-tasks add
When adding a task:
- Generate a unique task ID (format:
task-XXX) - Ask for any missing required info:
- Title (required)
- Due date (required — always set one, even if approximate)
- Goal alignment (recommended — which goal does this advance?)
- Priority (default: 3/normal)
- Description (optional — helpful for complex tasks)
- Write the task to
~/.claude/my-tasks.yaml - Confirm: "Added: [title] — due [date] — aligned to [goal]"
Goal alignment validation:
Check ~/.claude/goals.yaml for active goals. If the task doesn't align
with any active goal, flag it: "This task doesn't align with your current goals.
Still want to add it?" This isn't a blocker — just a prompt for intentionality.
/my-tasks complete
- Find the task by ID in
~/.claude/my-tasks.yaml - Update status to "complete"
- Add completion date
- Confirm: "Completed: [title]"
- If completed before due date, celebrate briefly: "Nice — finished 3 days early."
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.
- 13d ago First seen · 126 lines · 0 tokens per session scan A b2d6de6f4a7c
my-tasks is a command published in the GitHub repository mimurchison/claude-chief-of-staff (432 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,055 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
standup
Quick daily standup from today's Claude Code sessions — grouped by project, with cost and errors.
fire-todos
Capture, list, and manage todos during work sessions.
gsd:resume-work
Resume work from previous session with full context restoration.
todo.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
standup
A command that creates a daily stand-up report by summarizing recent work, planned tasks, calendar events, and blockers.
ops
Weekly operations loop — triage the inquiry inbox, advance the CRM pipeline, sweep open PRs across repos, and surface the content plan. Loads the ops skill.