premortem

premortem is a skill for Claude Code, Codex from rakovi4/continue-framework. It costs 42 tokens per session (546 once invoked), scanned A, original, MIT.

A review that imagines a newly shipped change caused an incident and then looks for the missing protection. It is a forward-looking check of gaps, separate from reviewing what the change already contains.

In plain words
What is it for?
Use it after a work unit or commit to explore possible incidents, identify the missing guard or test, and record concerns for later fixes.
Why use it?
It can reveal failures that ordinary code review may miss by focusing on how the change could break in real use. Findings become follow-up work without undoing the shipped change.

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/rakovi4/continue-framework/premortem
Any agent
npx skills add rakovi4/continue-framework --skill premortem
Clone the repo
git clone --depth 1 https://github.com/rakovi4/continue-framework

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 premortem

README.md
[![agentmods](https://agentmods.dev/badge/skills/rakovi4/continue-framework/premortem.svg)](https://agentmods.dev/skills/rakovi4/continue-framework/premortem)
Your own site
<a href="https://agentmods.dev/skills/rakovi4/continue-framework/premortem"><img src="https://agentmods.dev/badge/skills/rakovi4/continue-framework/premortem.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 546 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 $0.00042 $0.00546
Opus 5 $0.00021 $0.00273
Sonnet 5 $0.00008 $0.00109
Haiku 4.5 $0.00004 $0.00055

Measured 4d ago against content hash 1265712aa4f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

premortem 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 4d 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/premortem/SKILL.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/premortem — Imagine the Incident

A fresh-context pass that assumes the latest work shipped and caused an incident, then works backward to the gap. Distinct from /agent-review: that audits what the work contains; this imagines what it is missing. The two are complementary lenses, not a repeated read.

Usage

  • /premortem — review the latest work-unit commit (HEAD)
  • /premortem <ref> — review a specific commit or range

Workflow

  1. Load .claude/agents/premortem-agent.md.
  2. Resolve the diff: default to the last commit (HEAD); use <ref> if given.
  3. Dispatch named agent premortem-agent with the diff and one line of context on what the work unit did, and await its result before continuing. This skill must never return PASS before the review has actually run.
  4. Surface the agent's verdict: PASS is silent; CONCERNS/BLOCK list each imagined incident, its mechanism in the diff, and the named missing guard, as follow-ups. Findings never revert the commit.

Dispatch context

When an orchestrator (/continue) dispatches this as a boundary review pass, the agent runs concurrently with agent-review — two independent fresh-context reads of the same diff. The timing and the diff it reads in that path (every commit of the just-completed scenario or task step, dispatched in that boundary unit's /refactor batch — it does not run on mid-block units) are owned by /continue; see its "Boundary Review Passes" section. A deterministic triage predicate runs before that dispatch and may skip both passes for an inert boundary. When they do run, /continue reads each finding's fixability tag and consumes the SAFE subset in an inline auto-fix (a separate review-fix: commit), while a NEEDS_CLARIFICATION finding — the last resort, gated by .claude/templates/workflow/clarification-escalation-test.md — is resolved by a single batched boundary quiz; see its "Triage & Auto-Fix" section. Run standalone, this skill reviews HEAD (or <ref>) on demand. The agent is read-only; it reports, it does not edit.

Read the full file on GitHub · 44 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. 4d ago First seen · 44 lines · 42 tokens per session scan A 1265712aa4f4

Subscribe to this mod's changes

premortem is a skill published in the GitHub repository rakovi4/continue-framework (50 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 546 once invoked, about $0.0002 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 2026-08-30.

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