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/reviewgit 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/review)<a href="https://agentmods.dev/commands/rubin-johnson/retro/review"><img src="https://agentmods.dev/badge/commands/rubin-johnson/retro/review.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 | $0.00015 | $0.00892 |
| Opus 5 | $0.00008 | $0.00446 |
| Sonnet 5 | $0.00003 | $0.00178 |
| Haiku 4.5 | $0.00002 | $0.00089 |
Grade A, and why
review 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/review
You are reviewing the user's agentic coding log to surface patterns, track improvement, and generate CLAUDE.md rules.
Setup
- Determine the plugin root: use
${CLAUDE_PLUGIN_ROOT}if available, otherwise find theretroplugin directory containingscripts/db.py. - Set the DB script path:
"${CLAUDE_PLUGIN_ROOT}/scripts/db.py"
Data Gathering
Run these queries to gather data. If the user provided a filter (e.g., /log-review prompt or /log-review --project myapp), pass it through.
# Overall stats
echo '{}' | python3 "${CLAUDE_PLUGIN_ROOT}/scripts/db.py" stats
# Stats filtered by errors only
echo '{"type":"error"}' | python3 "${CLAUDE_PLUGIN_ROOT}/scripts/db.py" stats
# Stats filtered by successes only
echo '{"type":"success"}' | python3 "${CLAUDE_PLUGIN_ROOT}/scripts/db.py" stats
# Weekly trends
echo '{}' | python3 "${CLAUDE_PLUGIN_ROOT}/scripts/db.py" trends
# Recent entries (last 20)
echo '{"limit":20}' | python3 "${CLAUDE_PLUGIN_ROOT}/scripts/db.py" query
# All entries for pattern analysis
echo '{}' | python3 "${CLAUDE_PLUGIN_ROOT}/scripts/db.py" query
If the DB is empty or doesn't exist, say: "No entries yet. Use /retro:error or /retro:success to start tracking patterns."
Presentation
Present the review in this order:
1. Overview
- Total entries (errors vs successes)
- Date range covered
- Most active project(s)
2. Top Failure Modes
- Categories with 3+ errors, ranked by count
- For each: count, subcategory breakdown, example summary
3. Patterns
- Look for clusters: same category appearing across different projects or time periods
- Look for sequences: errors that tend to follow each other
- Call out any category where errors are INCREASING over recent weeks
4. Wins
- List successes, grouped by category
- Highlight any category where the user has both errors AND recent successes (milestone detection)
5. Milestone Detection
For any category where the user has errors AND recent successes (successes logged AFTER the errors), call it out:
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 · 110 lines · 15 tokens per session scan A ee649e3bedb1
review is a command published in the GitHub repository rubin-johnson/retro (2 stars, last pushed 4mo ago), licensed MIT. It adds 15 tokens to every session and 892 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
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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.