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-compoundgit 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-compound)<a href="https://agentmods.dev/commands/classicchins/compounding-marketing/cm-compound"><img src="https://agentmods.dev/badge/commands/classicchins/compounding-marketing/cm-compound.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 | $0.00000 | $0.01928 |
| Opus 5 | $0.00000 | $0.00964 |
| Sonnet 5 | $0.00000 | $0.00386 |
| Haiku 4.5 | $0.00000 | $0.00193 |
Grade A, and why
cm-compound 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 4d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cm-compound — Capture a Learning
Append a single, schema-valid learning entry to .agents/learnings/<category>.md so future marketing work in this category starts from prior evidence, not a blank page.
This command is the write side of the compounding loop. The read side is the Prior Learnings Consulted section that wired skills run before producing output. The schema both sides obey is defined in skills/_LEARNINGS_SCHEMA.md — that file is the source of truth; this command must conform to it.
When to use
Run /cm-compound immediately after:
- A campaign, page, launch, or experiment produced a clear result (good or bad).
- An A/B test reached significance — whether it won or lost. Losing tests are often higher-signal than winning ones.
- A round of customer research surfaced a non-obvious pattern.
- A surprise occurred — something behaved opposite to expectation.
Do not run it for routine deliveries that taught nothing new, or for opinions without evidence. The bar is captured evidence, not vibes.
What it does
- Walks the user through the six required fields for a learning entry.
- Validates each field against the schema (
_LEARNINGS_SCHEMA.md§"Required entry structure"). - Resolves the correct category file (
.agents/learnings/<category>.md), creating it with valid frontmatter if it does not exist. - Writes the new entry above existing entries (reverse-chronological).
- Updates frontmatter (
last_updated,entries_count). - Reports what was captured and which wired skills will now consume it.
Process
Step 1: Confirm there is a real learning to capture
Ask the user:
- What worked, what didn't, what surprised you, what would you do differently?
If the answer is generic ("the campaign went well") or non-falsifiable ("the brand feels stronger"), stop. Ask for the specific outcome, number, or quote that makes this a learning rather than an impression. A learning without evidence is noise.
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.
- 4d ago First seen · 154 lines · 0 tokens per session scan A 6efb0f41365f
cm-compound 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 1,928 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
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
session-end
I'll summarize this coding session and update the memory system with our accomplishments.
memory-store
Store an insight, decision, or pattern to memory.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.