postmortem-policy

postmortem-policy is a skill for Claude Code, Codex from EZotoff/ez-omo-config. It costs 55 tokens per session (752 once invoked), scanned A, original, MIT.

A guided incident-review workflow that turns a software failure or repeated agent mistake into a proposed change to instructions or policy. It traces the cause and requires explicit approval before editing anything.

In plain words
What is it for?
Use it after regressions, lost work, workflow failures, or repeated mistakes to document the cause, draft the smallest policy fix, and present it for an apply, revise, or drop decision.
Why use it?
It helps prevent the same failure from recurring without silently changing project rules. It also separates instruction problems from mistakes and tooling limitations.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md; mentions OpenCode.

Good fit Use it after regressions, lost work, workflow failures, or repeated mistakes to document the cause, draft the smallest policy fix, and present it for an apply, revise, or drop decision.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ezotoff/ez-omo-config/postmortem-policy
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.

Any agent
npx skills add EZotoff/ez-omo-config --skill postmortem-policy
Clone the repo
git clone --depth 1 https://github.com/EZotoff/ez-omo-config

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.

agentmods badge for postmortem-policy

README.md
[![agentmods](https://agentmods.dev/badge/skills/ezotoff/ez-omo-config/postmortem-policy/github.svg)](https://agentmods.dev/skills/ezotoff/ez-omo-config/postmortem-policy)
Your own site
<a href="https://agentmods.dev/skills/ezotoff/ez-omo-config/postmortem-policy"><img src="https://agentmods.dev/badge/skills/ezotoff/ez-omo-config/postmortem-policy/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 postmortem-policy

Your own site · 80×15
<a href="https://agentmods.dev/skills/ezotoff/ez-omo-config/postmortem-policy"><img src="https://agentmods.dev/badge/skills/ezotoff/ez-omo-config/postmortem-policy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 752 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 $0.00055 $0.00752
Opus 5 $0.00028 $0.00376
Sonnet 5 $0.00011 $0.00150
Haiku 4.5 $0.00006 $0.00075

Measured 3d ago against content hash 41348d9e6292, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

postmortem-policy 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/postmortem-policy/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Postmortem → Policy

Triggers: /postmortem-policy, postmortem, incident review, "how do we prevent this", "falling into this seam again"

The acceptance boundary (non-negotiable)

You may research, analyze, draft, and queue. You may NOT apply any amendment — no file edit, no wisdom write, no skill change — until the operator explicitly approves the specific diff you show. Output always terminates in a decision checkpoint: apply / revise / drop.

Workflow

1. Accept the incident

Input: an incident description, a log excerpt, a session reference, or just "the thing that just broke". If input is vague, reconstruct from the current session's recent history before asking questions.

2. Root cause

Establish the causal chain to the earliest preventable link — the point where an instruction, skill, config, or convention, if it had existed or been followed, would have prevented the incident. Distinguish:

  • agent error despite good instructions (no policy fix; note it),
  • missing or ambiguous instruction (policy candidate),
  • tooling gap no instruction can fix (escalate as infrastructure work, not policy).

3. Find the gap

Search where the fix would live, in this order:

  1. Project AGENTS.md files (repo root and ~/.config/opencode/AGENTS.md)
  2. Existing skills (~/.config/opencode/skills/*/SKILL.md)
  3. Wisdom store (~/.sisyphus/scripts/wisdom-search.sh "<keywords>")

If a rule already exists and was ignored, the incident is an enforcement problem — say so; do not write a duplicate rule.

4. Propose the minimal amendment

Exactly one of:

  • an AGENTS.md edit (show old → new lines, minimal delta),
  • a skill patch (file + section),
  • a new wisdom entry (use wisdom-write.sh semantics; show the entry text).

Read the full file on GitHub · 60 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. 3d ago First seen · 60 lines · 55 tokens per session scan A 41348d9e6292

Subscribe to this mod's changes

postmortem-policy is a skill published in the GitHub repository EZotoff/ez-omo-config (5 stars, last pushed 4d ago), licensed MIT. It adds 55 tokens to every session and 752 once invoked, about $0.0003 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 2026-09-06.