postmortem

A postmortem tool that turns the current conversation into seven structured files for a Ralphy project. A postmortem is a written review of what happened, what was learned, and what should change.

In plain words
What is it for?
Use it after a Ralphy project to document the conversation, lessons, model and cost choices, CLI issues, workflow fixes, completed units, and related project records.
Why use it?
Separating the record by audience keeps lessons, tool problems, workflow fixes, completed work, and the conversation history easier to find and reuse.

Skill for Claude CodeCodex

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/alecs5am/ralphy/postmortem
Any agent
npx skills add alecs5am/ralphy --skill postmortem
Clone the repo
git clone --depth 1 https://github.com/alecs5am/ralphy

Made for: Claude Code, Codex.

Per session 292 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,556 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 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 $0.00292 $0.04556
Opus 5 $0.00146 $0.02278
Sonnet 5 $0.00058 $0.00911
Haiku 4.5 $0.00029 $0.00456

Measured 2d ago against content hash be56ccc48fc0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

postmortem scanned grade A 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

description: Distil the conversation we just had into a structured 7-file postmortem set under `.ralphy/workspaces/<ws>/projects/<id>/postmortem/` for the active ralphy project. Splits the record into chronological chat
.agents/skills/postmortem/SKILL.md · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Postmortem skill — ralphy pipeline

Why multi-doc

A single POSTMORTEM.md mixes very different audiences:

  • Future-me on the next similar project wants lessons + model picks + prompt patterns (02-lessons.md, 04-models-and-cost.md).
  • The user reviewing what we actually did wants a chronological replay of their asks and the agent's steps (01-chat-history.md).
  • A CLI maintainer wants a clean list of ralphy verbs that failed or didn't exist, plus the raw workaround used (03-cli-issues.md). This is the highest-leverage doc — it's what turns the session into a CLI roadmap.
  • The playbook author wants meta-level where did the workflow break, what doc was wrong / missing (05-workflow-fixes.md).
  • The extract / publish step (templater, the publish-entity.ts path #056) wants a clean record of which finished Units the project shipped and the provenance blocks behind each (06-units.md). It freezes the entity facts while fresh so they can be classified + published later without re-deriving them.

When you stuff all of these into one file, the CLI-issues list and the units record get buried in a 500-line rules document and never make it into a PR. The split is so each doc can be skimmed by the right reader.

When to fire

Hard triggers (always do it):

  • User types /postmortem
  • "write a postmortem", "retro this", "what did we learn", "write up the lessons", "debrief"

Proactive triggers (offer to do it, don't auto-execute):

  • Session has had ≥2 user corrections ("don't like it", "2/10", "redo it") AND a project ID was active
  • ≥1 instance of the agent reaching past ralphy (raw bunx tsx against a TS file, raw ffmpeg, raw curl against a provider) — that's a CLI gap and the session must document it before it's lost
  • User says "well that's about it" / "project is done" after a long iteration session
  • After a ralphy render succeeds at the end of a multi-iteration session

What I produce

A directory at .ralphy/workspaces/<ws>/projects/<id>/postmortem/ with 7 files:

Read the full file on GitHub · 236 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. 2d ago First seen · 236 lines · 292 tokens per session scan A be56ccc48fc0

Subscribe to this mod's changes

postmortem is a skill published in the GitHub repository alecs5am/ralphy (128 stars, last pushed 7d ago), licensed Apache-2.0. It adds 292 tokens to every session and 4,556 once invoked, about $0.0015 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.