pi-lens: Skill for Claude Code

.claude/skills/retro/SKILL.md

retro is a skill for Claude Code from apmantza/pi-lens. It costs 89 tokens per session (498 once invoked), scanned A, original, MIT.

A retrospective procedure for turning a coding session, incident, or merged bug fix into changes to checks, hooks, contracts, or documentation. A retrospective is a structured review of what went wrong and how to prevent it happening again.

In plain words
What is it for?
Use it after incidents or bug fixes to review evidence, classify mistakes, add tests or CI checks, update role guidance, and record unresolved recurrence issues.
Why use it?
It helps teams address recurring mistakes with concrete safeguards instead of merely recording lessons. It distinguishes automatic checks from decisions that still require human judgment.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is apmantza/pi-lens's own configuration. It tells Claude Code how to work on pi-lens itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pi-lens configures →

Reuse

Borrowing it

Nothing to install: this file belongs to apmantza/pi-lens. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/apmantza/pi-lens/master/.claude/skills/retro/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/apmantza/pi-lens

Made for: Claude Code.

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/apmantza/pi-lens/retro/github.svg)](https://agentmods.dev/skills/apmantza/pi-lens/retro)
Your own site
<a href="https://agentmods.dev/skills/apmantza/pi-lens/retro"><img src="https://agentmods.dev/badge/skills/apmantza/pi-lens/retro/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for retro

Your own site · 80×15
<a href="https://agentmods.dev/skills/apmantza/pi-lens/retro"><img src="https://agentmods.dev/badge/skills/apmantza/pi-lens/retro.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 498 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00089 $0.00498
Opus 5.5 $0.00036 $0.00199
Sonnet 5.5 $0.00018 $0.00100
Haiku 4.5 $0.00009 $0.00050

Measured 1mo ago against content hash 40a800a14e36, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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.

.claude/skills/retro/SKILL.md · 45 lines

What it actually says

Retro

Source of truth: docs/pi-lens-retro.md. This file is the invocation procedure; on any conflict the contract wins.

Invoke

/retro with no argument runs over the current session's ledger and transcripts. /retro <PR|issue|run id|"incident: ..."> scopes it to one incident. The retro is read-only on the repo except for the outputs the contract names.

Steps

  1. Read docs/pi-lens-retro.md in full, then the inputs it names for the scope: ledger, transcripts, PR bodies and verdicts, CI logs on the exact head.
  2. Collect candidates by category; skip categories with no evidence.
  3. Classify each candidate mechanical or judgement. Mechanical is the default.
  4. Mechanical: build the check now when it is contained (governance test, hook, CI job, preflight row) and paste its red on the incident's shape and its mutation transcript; otherwise file it with the recurrence named. Judgement: one line in the catalog or the owning role contract.
  5. Steering audit: every no-op line names the decision it changed or is deleted.
  6. Record one mistake row per distinct mistake in docs/pi-lens-merge-policy.md ("Common mistakes").
  7. Report the fixed-shape table (Finding, Evidence, Class, Deliverable, Status) ordered by severity, and the list of changes made or filed. When delegated without Git authority, hand off through RETRO.md at the worktree root.

Do not

  • Ship a check without its red transcript.
  • Write a rule for a mechanical mistake.
  • Create a new home for rules; the catalog, the role contracts, and the merge-policy mistake table are the only three.
  • Mix the retro with implementation or review in one delegation.
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. 1mo ago Changed 40a800a14e36
  2. 1mo ago First seen · 45 lines · 89 tokens per session scan A e350cfae9142

Subscribe to this mod's changes

retro is a skill published in the GitHub repository apmantza/pi-lens (514 stars, last pushed yesterday), licensed MIT. It adds 89 tokens to every session and 498 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-16.

Related

retro compared with skills from other repositories

retro next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
retroapmantza/pi-lensSkill514yesterdayMITA89Claude Code
systematic-debuggingopen-metadata/OpenMetadataSkill16kyesterdayApache-2.0A37Claude Code
log-error-digestzebbern/claude-code-guideSkill4.7k3d agoMITA71Claude Code, Codex
cwv-optimizeradobe/skillsSkill319yesterdayApache-2.0A112Claude Code
ci-fixersipyourdrink-ltd/bernsteinSkill1.2kyesterdayApache-2.0A15Claude Code, Codex
incident-response-incident-responsermyndharis/antigravity-skillsSkill1.9k23d agoMITA36Claude Code
triaging-web-analytics-supportPostHog/posthogSkill41kyesterdaynoneA151Claude Code, Codex