retro

retro is a skill for Claude Code, Codex from sandsower/beislid. It costs 81 tokens per session (1,271 once invoked), scanned A, original, MIT.

A workflow for reflecting on a completed software run or session and recommending changes to the project's development process. It examines available evidence and workflow configuration.

In plain words
What is it for?
Use it to suggest improvements to workflow rules, checks, and handoffs without directly editing the project configuration.
Why use it?
It helps find steps that were missing, noisy, slow, confusing, or unnecessary after work is finished.

Skill for Claude CodeCodex

Part of the beislid plugin — 22 skills 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 skills/sandsower/beislid/retro
Any agent
npx skills add sandsower/beislid --skill retro
Clone the repo
git clone --depth 1 https://github.com/sandsower/beislid

Made for: Claude Code, Codex.

Or install beislid, the plugin that ships this one along with the rest of its 22 skills.

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/sandsower/beislid/retro.svg)](https://agentmods.dev/skills/sandsower/beislid/retro)
Your own site
<a href="https://agentmods.dev/skills/sandsower/beislid/retro"><img src="https://agentmods.dev/badge/skills/sandsower/beislid/retro.svg" alt="Measured on agentmods" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,271 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 $0.00081 $0.01271
Opus 5 $0.00041 $0.00635
Sonnet 5 $0.00016 $0.00254
Haiku 4.5 $0.00008 $0.00127

Measured 3d ago against content hash a7d871504ec2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 3d 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.

skills/retro/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Retro

Turn a run or session into workflow-improvement recommendations. retro answers: what should change about this repo's Beislið workflow after what we just learned?

retro is recommendation-only. It never edits .beislid/workflow.md; setup remains the canonical config writer.

Use this for:

  • Post-run/session reflection
  • Gate tuning suggestions
  • Workflow default refinement
  • Reviewing skipped, noisy, missing, slow, or ambiguous workflow steps
  • Preparing a handoff for a later setup run

Do not use this for:

  • Checking whether config is valid or probes pass — use doctor
  • Direct config editing — use setup
  • Product shaping — use spec
  • PR readiness gates — use ready-for-review

Process

1. Load available context

Inspect before interviewing. Use what the current host and repo provide, then ask only for missing high-value context.

Collect, when available:

  • Current user request and any extra notes they supplied
  • Current session context, including recent gate/review/setup friction already visible in chat
  • Git repo root, branch, status, and changed-file summary
  • <repo>/.beislid/workflow.md as the current workflow baseline
  • .beislid/checkpoints/latest.json and readable referenced checkpoint artifacts
  • Beislið run-ledger summaries or final reports for relevant recent runs, if the CLI/state is available
  • Session-memory or memento notes, if the host exposes memory/search tools
  • Recent local evidence such as gate output summaries, skipped checks, accepted risks, or repeated manual prompts

If a source is missing, unavailable, stale, or too expensive to inspect, say so briefly and continue with the evidence you have. Do not fail solely because durable context is absent.

2. Compare evidence to workflow config

Review the whole workflow, not just gates. Look for friction in:

  • ticket source and branch detection
  • scopes, gate sets, gate metadata, cost, selectors, and parallel-safety hints
  • lifecycle/checkpoint artifacts
  • action policy prompts or unsafe defaults
  • PR review/update paths
  • final check and review handoff behavior
  • model routing disclosures or repeated model-fit issues
  • setup/doctor discoverability gaps
  • prose in workflow.md that should encode a default, warning, or team preference

Read the full file on GitHub · 133 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 3d ago First seen · 133 lines · 81 tokens per session scan A a7d871504ec2

Subscribe to this mod's changes

retro is a skill published in the GitHub repository sandsower/beislid (10 stars, last pushed 4d ago), licensed MIT. It adds 81 tokens to every session and 1,271 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens