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/rubin-johnson/retro/successgit clone --depth 1 https://github.com/rubin-johnson/retroWrote 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/rubin-johnson/retro/success)<a href="https://agentmods.dev/commands/rubin-johnson/retro/success"><img src="https://agentmods.dev/badge/commands/rubin-johnson/retro/success.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 | $0.00010 | $0.00612 |
| Opus 5 | $0.00005 | $0.00306 |
| Sonnet 5 | $0.00002 | $0.00122 |
| Haiku 4.5 | $0.00001 | $0.00061 |
Grade A, and why
success 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/success
You are logging an agentic coding success. The goal is to capture what the user did RIGHT so the pattern can be repeated and eventually promoted to a CLAUDE.md rule.
Setup
- Load the
agentic-interviewskill for taxonomy and interview methodology. - Determine the plugin root: use
${CLAUDE_PLUGIN_ROOT}if available, otherwise find theretroplugin directory containingscripts/db.py.
Interview Flow
Step 1: Review Context
Before asking anything, review the recent conversation. Look for:
- What worked well
- What the user did that led to a good outcome
- Specific techniques or patterns that were effective
If the user provided an optional description with the command, use it as a starting point.
Step 2: Conduct Interview
Ask 2-4 specific questions, one at a time, using AskUserQuestion.
Essential questions (pick the most relevant):
- "What specifically did you do that led to this good outcome?"
- "Can you paste or paraphrase the prompt/approach that worked?"
- "Why do you think this worked where other approaches might not have?"
- "Is this something you'd want to repeat? What makes it repeatable?"
Step 3: Capture What Worked
Get the specific technique, prompt, or approach verbatim. This is the pattern to preserve.
Step 4: Propose Category
Based on the conversation and interview answers, propose a category and subcategory from the success taxonomy. Frame it as: "This looks like a category/subcategory win -- [brief explanation]. Sound right?"
Use AskUserQuestion with the proposed category as the recommended option and 2-3 alternatives.
Step 5: Confirm and Write
Present a summary of what will be logged:
- Summary: One-line description
- Category: category/subcategory
- What worked: The specific technique
- Why it worked: The underlying principle
Ask the user to confirm with AskUserQuestion.
Step 6: Write to Database
Run:
echo '<json_payload>' | python3 "${CLAUDE_PLUGIN_ROOT}/scripts/db.py" log-success
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 · 78 lines · 10 tokens per session scan A 32c3412c761c
success is a command published in the GitHub repository rubin-johnson/retro (2 stars, last pushed 4mo ago), licensed MIT. It adds 10 tokens to every session and 612 once invoked, about $0.0001 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 2026-08-31.
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.
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.
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.