cm-retro

cm-retro is a command for Claude Code from classicchins/compounding-marketing. It costs 0 tokens per session (904 once invoked), scanned A, original, MIT.

A structured retrospective, or post-mortem, for reviewing a campaign, product launch, experiment, or sprint after it ends. It compares intended results with actual results and examines what caused them.

In plain words
What is it for?
Use it to review targets and outcomes, identify what to continue or stop, explain why results happened, and decide what to change next time.
Why use it?
It turns past work into specific lessons instead of leaving successes, failures, and next steps undocumented.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument.

Part of the compounding-marketing plugin — 39 skills, 16 commands shipped together

Install

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.

agentmods
npx agentmods add commands/classicchins/compounding-marketing/cm-retro
Clone the repo
git clone --depth 1 https://github.com/classicchins/compounding-marketing

Made for: Claude Code.

Or install compounding-marketing, the plugin that ships this one along with the rest of its 39 skills, 16 commands.

Wrote 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.

agentmods badge for cm-retro

README.md
[![agentmods](https://agentmods.dev/badge/commands/classicchins/compounding-marketing/cm-retro.svg)](https://agentmods.dev/commands/classicchins/compounding-marketing/cm-retro)
Your own site
<a href="https://agentmods.dev/commands/classicchins/compounding-marketing/cm-retro"><img src="https://agentmods.dev/badge/commands/classicchins/compounding-marketing/cm-retro.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 904 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00904
Opus 5 $0.00000 $0.00452
Sonnet 5 $0.00000 $0.00181
Haiku 4.5 $0.00000 $0.00090

Measured 6d ago against content hash 83762d84c3ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

cm-retro 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 6d 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.

commands/cm-retro.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/cm:retro — Campaign / Sprint Retrospective

Structured post-mortem for campaigns, launches, or sprints.

What It Does

A deeper analysis than /cm:compound. While compound captures quick learnings, retro does a full post-mortem: what happened, why it happened, what to change. Best run after campaigns, launches, or sprint cycles.

Time Investment

20-30 minutes

Process

1. Set the Scope

  • What are we reviewing? (Campaign name, sprint #, launch, experiment)
  • What was the timeline? (Start → end)
  • What was the original goal?
  • What was the actual outcome?

2. Results vs. Expectations

Metric Target Actual Delta Verdict
[Primary metric] ... ... ... 🟢/🟡/🔴
[Secondary metric] ... ... ... 🟢/🟡/🔴
[Secondary metric] ... ... ... 🟢/🟡/🔴

Overall: Did we hit the goal? Why or why not?

3. What Worked (Keep Doing)

List things that went well. Be specific — not "content was good" but "the comparison blog post drove 340 signups at $2.40 CAC."

For each:

  • What specifically worked?
  • Why did it work?
  • How can we do more of this?
  • Can this be systematized?

4. What Didn't Work (Stop Doing)

List things that failed or underperformed. No blame — just facts.

For each:

  • What happened?
  • Why didn't it work? (Root cause, not surface)
  • How much time/money was spent?
  • Should we try again differently, or kill it?

5. What We'd Change (Start Doing)

Based on the above:

  • What would we do differently if we ran this again?
  • What new approach should we try?
  • What process changes would improve execution?

6. Surprises & Insights

Things you didn't expect — both good and bad:

  • Unexpected channel that worked
  • Audience segment that responded differently
  • Content format that surprised
  • Timing or sequencing insight

7. Action Items

Concrete next steps:

Action Owner Deadline Priority
[Action] [Who] [When] High/Med/Low
... ... ... ...

Read the full file on GitHub · 139 lines

Changes

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.

  1. 6d ago First seen · 139 lines · 0 tokens per session scan A 83762d84c3ed

Subscribe to this mod's changes

cm-retro is a command published in the GitHub repository classicchins/compounding-marketing (8 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 904 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.