retro

retro is a skill for Claude Code from Borda/AI-Rig. It costs 40 tokens per session (6,491 once invoked), scanned C, original, Apache-2.0.

A read-only report generator for reviewing completed machine-learning improvement runs. It reads experiment records and calculates whether observed changes are statistically meaningful.

In plain words
What is it for?
Use it after a run to compare experiments from the same program and metric, identify ineffective iterations, summarize lessons, and create ideas for the next tests.
Why use it?
It helps distinguish real improvements from random variation, stalled attempts, suspicious jumps, and results that need further investigation.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the research plugin — 8 skills, 2 agents shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Borda/AI-Rig
Claude Code
/plugin install research

Made for: Claude Code.

Or install research, the plugin that ships this one along with the rest of its 8 skills, 2 agents.

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 retro

README.md
[![agentmods](https://agentmods.dev/badge/skills/borda/ai-rig/retro.svg)](https://agentmods.dev/skills/borda/ai-rig/retro)
Your own site
<a href="https://agentmods.dev/skills/borda/ai-rig/retro"><img src="https://agentmods.dev/badge/skills/borda/ai-rig/retro.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,491 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00040 $0.06491
Opus 5 $0.00020 $0.03245
Sonnet 5 $0.00008 $0.01298
Haiku 4.5 $0.00004 $0.00649

Measured 6d ago against content hash 736a8e7b9f30, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

retro scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- Retro run dirs don't write `result.jsonl` — exempt from automated 30-day TTL cleanup (exempt per `.claude/rules/foundry-artifact-lifecycle.md` — no `result.jsonl` = cleanup skipped); remove manually when done (`rm -rf
plugins/cc_research/skills/retro/SKILL.md · 391 lines

How it starts

The opening of the file, as written. The whole thing — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Post-run retrospective analysis. After /research:run completes, reads .experiments/state/<run-id>/experiments.jsonl, computes statistical significance, detects dead iterations, flags suspicious metric jumps, generates learning summary with next-hypothesis queue.

NOT for: running experiments (use /research:run); designing experiments (use /research:plan); validating methodology (use /research:judge); verifying paper implementation (use /research:verify); comparing runs from different programs/goals — --compare valid only for same-program, same-metric runs. Read-only — never modifies code, commits, or experiment state.

Agent Resolution

Agent resolution: load and follow the protocol below. Contains: foundry check + fallback table. research:scientist in same plugin — no fallback needed if research plugin installed.

export CSID="${CLAUDE_CODE_SESSION_ID:-$PPID}"
_RESEARCH_SHARED=$(python "${CLAUDE_PLUGIN_ROOT:-plugins/cc_research}/bin/resolve_shared.py" 2>/dev/null)  # timeout: 5000
[ -z "$_RESEARCH_SHARED" ] && { echo "! Plugin path resolution failed — ensure research plugin installed and CLAUDE_PLUGIN_ROOT set, or invoke /research:retro from project root."; exit 1; }
echo "$_RESEARCH_SHARED" > "${TMPDIR:-/tmp}/research-shared-${CSID}"  # cold resolve — every later site reads this sentinel instead of re-running python
cat "$_RESEARCH_SHARED/agent-resolution.md"

Retro Mode (Steps T1–T7)

Triggered by retro, retro <run-id>, or retro <run-id> --compare <run-id-2>.

Defaults: --threshold 0.001, --alpha 0.05.

Unsupported flag check: load and follow the protocol below. Supported flags for this skill: --compare, --threshold, --alpha.

# loads: unsupported-flag-protocol.md
export CSID="${CLAUDE_CODE_SESSION_ID:-$PPID}"
IFS= read -r _RESEARCH_SHARED < "${TMPDIR:-/tmp}/research-shared-${CSID}" 2>/dev/null || _RESEARCH_SHARED=""  # warm read (Check 41)
cat "$_RESEARCH_SHARED/unsupported-flag-protocol.md"

Read the full file on GitHub · 391 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 · 391 lines · 40 tokens per session scan C 736a8e7b9f30

Subscribe to this mod's changes

retro is a skill published in the GitHub repository Borda/AI-Rig (26 stars, last pushed 2d ago), licensed Apache-2.0. It adds 40 tokens to every session and 6,491 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.