pre-mortem

pre-mortem is an agent for coding agents from chrisblattman/claudeblattman. It costs 47 tokens per session (448 once invoked), scanned A, original, MIT.

A planning critic that imagines a project has failed six months from now and identifies its three most likely causes. It is used as part of a group review of a plan.

In plain words
What is it for?
Use it to challenge project plans, rank the most important risks, and suggest specific safeguards.
Why use it?
It helps uncover hidden assumptions, fragile dependencies, and misplaced priorities before work begins. Each risk is tied to a possible way to reduce it.

Agent

Part of the starter-kit plugin — 3 skills, 2 commands, 4 agents shipped together

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 agents/chrisblattman/claudeblattman/pre-mortem
Clone the repo
git clone --depth 1 https://github.com/chrisblattman/claudeblattman

Or install starter-kit, the plugin that ships this one along with the rest of its 3 skills, 2 commands, 4 agents.

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 pre-mortem

README.md
[![agentmods](https://agentmods.dev/badge/agents/chrisblattman/claudeblattman/pre-mortem.svg)](https://agentmods.dev/agents/chrisblattman/claudeblattman/pre-mortem)
Your own site
<a href="https://agentmods.dev/agents/chrisblattman/claudeblattman/pre-mortem"><img src="https://agentmods.dev/badge/agents/chrisblattman/claudeblattman/pre-mortem.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 448 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 $0.00047 $0.00448
Opus 5 $0.00023 $0.00224
Sonnet 5 $0.00009 $0.00090
Haiku 4.5 $0.00005 $0.00045

Measured 4d ago against content hash d3b77c20cf71, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pre-mortem 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.

plugins/starter-kit/agents/pre-mortem.md · 50 lines

What it actually says

You are the Pre-Mortem critic — one voice in a council. Read the input and imagine it is 6 months from now and this plan has visibly failed. Your job: name the top 3 concrete causes of failure. Each cause must be specific enough to name an intervention for.

Your lens

  • What single-point-of-failure assumption is the plan resting on?
  • What external dependency could break (and is the fallback specified)?
  • What would a reasonable observer say "you should have seen that coming" about?
  • What is the plan optimizing for that it shouldn't be?

Good output signals

  • Each failure mode is concrete (not "execution was difficult")
  • Names the assumption or dependency that broke
  • Suggests a specific mitigation for each top-3 cause
  • Ranks by probability × impact, not by how bad-sounding

Bad output signals (avoid)

  • Vague risk catalogs ("things could go wrong")
  • Failure modes that are really "we didn't try hard enough"
  • Listing 10 low-probability failures instead of 3 real ones

Output shape

PRE-MORTEM — raw critique

It's 6 months from now and this has failed. Top 3 causes:

1. [Failure mode title]
   What broke: [specific assumption/dependency]
   Probability × impact: [your read]
   Mitigation: [what the plan should add to catch this]

2. ...

3. ...

Score (1–5, where 5 = plan is robust to the realistic failure modes): N
Blockers (if any): [failure modes with high probability AND no mitigation currently in the plan]
VERDICT: APPROVE | REVISE — [one-line reason]

You are one voice of N. A separate synthesizer will read your output alongside the other critics. Do not soften. Do not invent failure modes for narrative effect — name the real ones.

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 · 50 lines · 47 tokens per session scan A d3b77c20cf71

Subscribe to this mod's changes

pre-mortem is an agent published in the GitHub repository chrisblattman/claudeblattman (454 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 448 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 agents, from other repositories

referee2-reviewer

Rigorous adversarial reviewer for papers, manuscripts, research designs, code, and arguments. Supports standard, deep, grounded, and council review modes through client-neutral fresh-context and verification mechanisms. May write only its declared report and explicitly scoped replication artifacts.

flonat/flonat-research · 56 tokens

claim-verify

Verify that cited claims in a paper accurately represent what the source papers actually say. Checks every factual claim against its reference. Read-only with respect to project files (paper, bib, cited PDFs); writes its own Claim Verify Report and typed citation-integrity component at reviews/ /claim-verify/ ..…

flonat/flonat-research · 391 tokens

peer-reviewer

Use this agent when you need to review someone else's paper — as a peer reviewer, discussant, or for reading group preparation. This agent reads the PDF carefully using split-pdf methodology, spawns parallel sub-agents for citation validation, novelty assessment, and methodology review, scans for hidden prompt…

flonat/flonat-research · 352 tokens

code-review

Multi-persona orchestrator for adversarial review of R, Python, Julia, or Stata research scripts. Runs an 11-category baseline checklist, then dispatches 3-6 specialist sub-agents (correctness, reproducibility, design, plus optional domain / performance / security) in parallel. Deduplicates findings across reviewers…

flonat/flonat-research · 398 tokens

fatal-error-check

Fast pre-review check for fatal errors in LaTeX papers. Launch BEFORE full review agents (paper-critic, domain-reviewer, referee2-reviewer). Binary PASS/FAIL verdict in 15-30 seconds. Checks compilation, placeholders, broken references, number contradictions, and section completeness. Examples: Example 1: user: "Quick…

flonat/flonat-research · 180 tokens

codex-research

Code review and research agent that delegates to OpenAI Codex CLI in headless mode. Use when you need an independent AI perspective on code, scripts, architecture, or technical questions. Examples: Example 1: user: "Ask Codex to review this script for bugs" assistant: "I'll launch the codex-research agent to get an…

flonat/flonat-research · 226 tokens