premortem

premortem is a skill for Claude Code from a-tokyo/agent-skills-harness. It costs 14 tokens per session (2,961 once invoked), scanned A, a copy of premortem, MIT.

A structured risk-analysis method that imagines a project has already failed and asks why. It is based on the premortem technique associated with Gary Klein and Shreyas Doshi.

In plain words
What is it for?
Use it to review plans, pull requests, files, or designs before work begins. It supports quick analysis for smaller decisions and deeper analysis for major implementations.
Why use it?
It helps uncover failure modes before implementation, including risks that are obvious, overlooked, or difficult to discuss. It also requires checking that suspected risks are real before flagging them.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; installed under .agents/ (shared by several agents).

Good fit Use it to review plans, pull requests, files, or designs before work begins. It supports quick analysis for smaller decisions and deeper analysis for major implementations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/a-tokyo/agent-skills-harness/premortem
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 a-tokyo/agent-skills-harness --skill premortem
Clone the repo
git clone --depth 1 https://github.com/a-tokyo/agent-skills-harness

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 premortem

README.md
[![agentmods](https://agentmods.dev/badge/skills/a-tokyo/agent-skills-harness/premortem/github.svg)](https://agentmods.dev/skills/a-tokyo/agent-skills-harness/premortem)
Your own site
<a href="https://agentmods.dev/skills/a-tokyo/agent-skills-harness/premortem"><img src="https://agentmods.dev/badge/skills/a-tokyo/agent-skills-harness/premortem/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 premortem

Your own site · 80×15
<a href="https://agentmods.dev/skills/a-tokyo/agent-skills-harness/premortem"><img src="https://agentmods.dev/badge/skills/a-tokyo/agent-skills-harness/premortem.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,961 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 100% copy Near-identical to another mod 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 $0.00014 $0.02961
Opus 5 $0.00007 $0.01481
Sonnet 5 $0.00003 $0.00592
Haiku 4.5 $0.00001 $0.00296

Measured 11d ago against content hash ee0f02aad104, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 11d 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.

Origin

This is a copy

100% identical to premortem — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/premortem/SKILL.md · 452 lines

How it starts

The opening of the file, as written. The whole thing — 452 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pre-Mortem

Identify failure modes before they occur by systematically questioning plans, designs, and implementations. Based on Gary Klein's technique, popularized by Shreyas Doshi (Stripe).

Usage

/premortem              # Auto-detect context, choose depth
/premortem quick        # Force quick analysis (plans, PRs)
/premortem deep         # Force deep analysis (before implementation)
/premortem <file>       # Analyze specific plan or code

Core Concept

"Imagine it's 3 months from now and this project has failed spectacularly. Why did it fail?"

Risk Categories (Shreyas Framework)

Category Symbol Meaning
Tiger [TIGER] Clear threat that will hurt us if not addressed
Paper Tiger [PAPER] Looks threatening but probably fine
Elephant [ELEPHANT] Thing nobody wants to talk about

CRITICAL: Verify Before Flagging

Do NOT flag risks based on pattern-matching alone. Every potential tiger MUST go through verification.

The False Positive Problem

Common mistakes that create false tigers:

  • Seeing a hardcoded path without checking for if exists(): fallback
  • Finding missing feature X without asking "is X in scope?"
  • Flagging code at line N without reading lines N±20 for context
  • Assuming error case isn't handled without tracing the code

Verification Checklist (REQUIRED)

Before flagging ANY tiger, verify:

potential_finding:
  what: "Hardcoded path at line 42"

verification:
  context_read: true    # Did I read ±20 lines around the finding?
  fallback_check: true  # Is there try/except, if exists(), or else branch?
  scope_check: true     # Is this even in scope for this code?
  dev_only_check: true  # Is this in __main__, tests/, or dev-only code?

result: tiger | paper_tiger | false_alarm

If ANY verification check is "no" or "unknown", DO NOT flag as tiger.

Required Evidence Format

Every tiger MUST include:

tiger:
  risk: "<description>"
  location: "file.py:42"
  severity: high|medium
  # REQUIRED - what mitigation was checked and NOT found:
  mitigation_checked: "No exists() check, no try/except, no fallback branch"

Read the full file on GitHub · 452 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. 11d ago First seen · 452 lines · 14 tokens per session scan A ee0f02aad104

Subscribe to this mod's changes

premortem is a skill published in the GitHub repository a-tokyo/agent-skills-harness (10 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 2,961 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to premortem, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

create-notes

Write a note to {shareddir}/notes/ that future agents can actually act on. Use after every coral eval, when a heartbeat (reflect / consolidate / pivot) asks for a note, or when you discover a grader / build / runtime issue that future agents will hit. Covers 4 note variants (experiment / infra / focus / synthesis)…

Human-Agent-Society/CORAL · 217 tokens

arbor-agent-executor

Executor-dispatch phase for Arbor. Use when implementing an Idea Tree node through RunExecutor or RunExecutorParallel semantics: isolated git worktree, executor prompt construction, eval metadata injection, RunTraining policy, smoke/full evaluation, report parsing, artifact persistence, tree update, and insight…

RUC-NLPIR/Arbor · 63 tokens

arbor-agent-ideate

Strict IDEATE-stage skill for Arbor. Use immediately after TreeView(format="constraints") when drafting Idea Tree nodes, enforcing the ideadrafting and firstprinciplesprobe behavior, depth-aware idea levels, four-line TreeAddNode hypotheses, conflict checks, and self-filtering against shallow tweaks.

RUC-NLPIR/Arbor · 66 tokens

grid-ctf-ops

Operational knowledge for the gridctf scenario including strategy playbook, lessons learned, and resource references. Use when generating, evaluating, coaching, or debugging gridctf strategies.

greyhaven-ai/autocontext · 42 tokens

codex-autoresearch

Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…

leo-lilinxiao/codex-autoresearch · 80 tokens

baseline-comparison-audit

Audit whether a paper's baseline comparisons are COMPLETE, FAIR, and SIGNIFICANT: a required recent SOTA baseline is missing while 'best/SOTA' is claimed (HP-MISSING-BASELINE); a baseline is undertuned / given less compute-tuning-data, run at a mismatched config, or the equal-budget ablation-as-baseline is absent…

wanshuiyin/Anti-Autoresearch · 310 tokens