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/classicchins/compounding-marketing/cm-weeklygit clone --depth 1 https://github.com/classicchins/compounding-marketingWrote 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/classicchins/compounding-marketing/cm-weekly)<a href="https://agentmods.dev/commands/classicchins/compounding-marketing/cm-weekly"><img src="https://agentmods.dev/badge/commands/classicchins/compounding-marketing/cm-weekly.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 5.1 | $0.00000 | $0.00945 |
| Opus 5 | $0.00000 | $0.00473 |
| Sonnet 5 | $0.00000 | $0.00189 |
| Haiku 4.5 | $0.00000 | $0.00094 |
Grade A, and why
cm-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 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cm:weekly — Weekly Marketing Review
Comprehensive weekly review to find patterns, plan ahead, and compound learnings.
What It Does
A 30-45 minute weekly review that synthesizes marketing activity, identifies patterns, celebrates wins, diagnoses problems, and plans the next week. This is where marketing knowledge compounds.
Process
1. Week in Review
Activity Audit:
- What content was published?
- What campaigns ran?
- What experiments completed?
- What shipped vs. what slipped?
Metrics Review:
- Traffic: This week vs. last week
- Signups/Leads: This week vs. last week
- Conversion rate: Any changes?
- Revenue impact: Attributable marketing contribution?
Wins:
- What worked really well?
- Any unexpected successes?
- What should you do more of?
Losses:
- What didn't work?
- What underperformed expectations?
- What should you stop or change?
2. Pattern Recognition
Themes:
- What topics or angles resonated?
- What channels performed best?
- What time of day/week worked best?
Learnings:
- What did you learn about your audience?
- What did you learn about your product positioning?
- What copywriting patterns worked?
Energy Audit:
- What marketing work energized you?
- What drained you?
- What should you delegate or automate?
3. Next Week Planning
Priorities:
- What are the 3 most important marketing tasks?
- What's the ONE thing that would make next week a success?
Calendar:
- Any launches or deadlines?
- Any campaigns to start/stop?
- Any content to publish?
Experiments:
- What are you testing next week?
- What hypothesis are you validating?
4. Compound Learnings
If any strong patterns emerged:
- Update
.agents/learnings/[category].md - Note what worked and why
- Create reusable template or process if applicable
Output Format
# Weekly Marketing Review — Week of [Date]
## This Week's Activity
- **Content published:** [count] — [list]
- **Campaigns active:** [list]
- **Experiments run:** [list]
- **Shipped vs. planned:** [X/Y]
## Metrics Summary
| Metric | This Week | Last Week | Change |
|--------|-----------|-----------|--------|
| Traffic | X | Y | +/-% |
| Signups | X | Y | +/-% |
| Conv. Rate | X% | Y% | +/-% |
| [Key metric] | X | Y | +/-% |
## Wins 🏆
1. [Win 1] — Why it worked: [reason]
2. [Win 2] — Why it worked: [reason]
## Losses 📉
1. [Loss 1] — What to change: [action]
2. [Loss 2] — What to change: [action]
## Patterns Identified
- **What resonated:** [topic/angle/format]
- **Best channel:** [channel + why]
- **Audience insight:** [learning]
## Energy Audit
- **Energizing:** [activities]
- **Draining:** [activities]
- **To delegate/automate:** [candidates]
## Next Week's Plan
### Top 3 Priorities
1. [Priority 1] — [expected outcome]
2. [Priority 2] — [expected outcome]
3. [Priority 3] — [expected outcome]
### Calendar
- [Day]: [Activity]
- [Day]: [Activity]
### Experiments
- Testing: [hypothesis]
- Success criteria: [metric + threshold]
## Learnings to Compound
- [Learning 1] → saved to `learnings/[category].md`
- [Learning 2] → [action]
## Open Questions
- [Question to explore]
- [Thing to research]
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 · 155 lines · 0 tokens per session scan A 135b7844e865
cm-weekly is a command published in the GitHub repository classicchins/compounding-marketing (7 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 945 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 2026-08-31.
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.