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/derek-larson14/delegate/weeklygit clone --depth 1 https://github.com/derek-larson14/delegateWhat 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 | $0.00006 | $0.00643 |
| Opus 5 | $0.00003 | $0.00321 |
| Sonnet 5 | $0.00001 | $0.00129 |
| Haiku 4.5 | $0.00001 | $0.00064 |
Grade A, and why
weekly 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Weekly Review
Phase 1: Mechanical Review
- Git changes: Key commits and file reorganization from past 7 days (helpful to commit changes right before the review)
- Tasks completed vs. planned (check task tracking files for completed items)
- What got moved to archived/completed tasks vs remains incomplete?
- Check last week's review predictions vs reality
- Upcoming hard deadlines
Phase 2: Emotional Reality Check
Direct Questions
- What's causing the most unease right now?
- What am I afraid of doing?
- What am I unwilling to feel?
- What brought the most joy/energy this week?
Phase 3: Constraint Analysis
The Core Question
"What could be cut here?"
Constraint Check
- Money: What's the real number? When does it hit?
- Time: What's actually locked in vs. self-imposed?
- Energy: Where am I bleeding out vs. gaining strength?
- Reputation: Real risk vs. imagined risk?
Phase 4: Finding Unlocks
Collaboration Opportunities
- Who could I be reaching out to for help?
- What can be delegated/automated/eliminated?
Reframe Prompts
- What if the opposite were true?
- What would [trusted advisor] tell me to do?
- What's the 80/20 here?
Phase 5: Energy-Aware Priorities
Next Week's Priorities
When coming up with this list think about:
- What MUST happen (external commitment)
- What unlocks everything else
- What maintains momentum
- What preserves energy/sanity
Energy Management
- Protected recharge time:
- Power hours for deep work:
- Batching strategy:
- Hard stops:
Evolution Tracking
Review Journey
Started thinking: Ended with: Key unlock: Pattern to remember:
REVIEW STRUCTURE
This should feel like a conversation between you and your chief of staff managing the weekly debrief meeting. The AI should propose questions, help you see things clearly, and work together on what comes next and how to think about the upcoming week.
Think about the above questions - go over what is important together.
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 · 87 lines · 6 tokens per session scan A 09d45cfd2d1d
weekly is a command published in the GitHub repository derek-larson14/delegate (39 stars, last pushed 4mo ago), licensed MIT. It adds 6 tokens to every session and 643 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.