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.

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.

Separating the record by audience keeps lessons, tool problems, workflow fixes, completed work, and the conversation history easier to find and reuse.

How alecs5am/ralphy configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to alecs5am/ralphy. 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/alecs5am/ralphy/main/.agents/skills/postmortem/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/alecs5am/ralphy

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/alecs5am/ralphy/postmortem/github.svg)](https://agentmods.dev/skills/alecs5am/ralphy/postmortem)

Your own site

<a href="https://agentmods.dev/skills/alecs5am/ralphy/postmortem"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/postmortem/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/alecs5am/ralphy/postmortem"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/postmortem.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

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. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 3 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 27
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
medium Excessive Agency · line 205
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
medium Excessive Agency · line 223
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00292	$0.04556
Opus 5.5	$0.00117	$0.01822
Sonnet 5.5	$0.00058	$0.00911
Haiku 4.5	$0.00029	$0.00456

Measured 1mo ago against content hash be56ccc48fc0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 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.

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

Files

What ships with it

8 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.

1mo 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 (140 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 292 tokens to every session and 4,556 once invoked, about $0.0012 per session on Opus 5.5. 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.

Debugging agent ai-agent ai-video bun ugc video-generation

smiles-validation

Strict SMILES validation, structural comparison, and modification verification. Catches invalid LLM-generated molecules.

synthetic-sciences/openscience · 24 tokens

gini-bug-report

File a locally-captured, already-redacted Gini crash report as a GitHub issue, with the user's consent. Reads the pending crash queue and delegates the actual filing to the github-issues skill.

Open-Curiosity/gini-agent · 47 tokens

phoenix-observability

Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.

synthetic-sciences/openscience · 47 tokens

video-gen

Use when generate videos with AI models — Runway, Kling, Sora, Pika, Seedance 2.0, Grok Imagine, Veo. Text-to-video, image-to-video, video extension, multi-modal references. Use when generating video from text prompts, animating images, or creating AI video content.

oyi77/1ai-skills · 69 tokens

poppify-troubleshoot

Diagnose a Poppify reel that came out wrong. Use when the user says: "the reel came out wrong", "render failed", "no audio in the video", "no music", "captions are missing", "wrong color text", "text is green/blue/etc instead of white", "video URL doesn't open", "video URL expired", "seeds were charged but no video"…

Poppify/poppify-claude-plugin · 0 tokens

poppify-schema-introspect

Inspect the deployed Poppify MCP tool schemas to verify what parameters are actually accepted. Use when: a parameter you passed seems to have been silently dropped, an applysessionpatch field didn't take effect, the render came out using defaults instead of your overrides, OR before recommending a parameter you're not…