Auto-Company is a software system that runs a recurring team of AI agents on a personal computer, where the agents plan work, make decisions, write code, deploy applications, and handle marketing. It is intended for autonomous product development on Windows, Linux, or macOS, using command-line agent tools and a local dashboard to track cycles and results. The catalogue entries are skills, agents, settings, and instructions that support this automated workflow.
Borrowing it
Nothing to install: this file belongs to MaxMiksa/Auto-Company. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/MaxMiksa/Auto-Company/main/.claude/skills/premortem/SKILL.mdgit clone --depth 1 https://github.com/MaxMiksa/Auto-CompanyWrote 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.
[](https://agentmods.dev/skills/maxmiksa/auto-company/premortem)<a href="https://agentmods.dev/skills/maxmiksa/auto-company/premortem"><img src="https://agentmods.dev/badge/skills/maxmiksa/auto-company/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.
<a href="https://agentmods.dev/skills/maxmiksa/auto-company/premortem"><img src="https://agentmods.dev/badge/skills/maxmiksa/auto-company/premortem.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00042 | $0.00521 |
| Opus 5.5 | $0.00017 | $0.00208 |
| Sonnet 5.5 | $0.00008 | $0.00104 |
| Haiku 4.5 | $0.00004 | $0.00052 |
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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-Mortem Analysis
Imagine the plan has completely failed, then work backward to identify what went wrong and how to prevent it.
Instructions
Set the scene: "It's [timeframe] in the future. This initiative was a complete disaster. Looking back, what happened?"
Generate failure scenarios without filtering for likelihood—get everything on the table first, then prioritize.
Output Format
The Plan Summarize what's being attempted and the success criteria.
Time Jump "It's [X months] later. This has failed completely. The outcome: [describe the disaster vividly]."
What Went Wrong
Generate 8-12 plausible failure causes across categories:
| Category | Failure Mode | How It Played Out |
|---|---|---|
| Execution | [What failed] | [The story of how] |
| External | [What failed] | [The story of how] |
| People | [What failed] | [The story of how] |
| Technical | [What failed] | [The story of how] |
| Assumptions | [What failed] | [The story of how] |
Risk Prioritization
| Failure Mode | Likelihood | Impact | Priority |
|---|---|---|---|
| ... | High/Med/Low | High/Med/Low | 1-5 |
Top 3 Risks & Mitigations
For each top risk:
- Risk: [Description]
- Early Warning Signs: What would indicate this is happening?
- Prevention: How to reduce likelihood
- Mitigation: How to reduce impact if it occurs
- Owner: Who's responsible for watching this?
Pre-Mortem Insights What did this exercise reveal that wasn't obvious before?
Revised Confidence After this analysis, how confident are you in success? What would increase confidence?
Guidelines
- Be vivid and specific—"the database corrupted" not "something went wrong"
- Include uncomfortable possibilities (key person leaves, competitor moves, we were wrong)
- Don't filter for "that won't happen"—the point is to surface hidden concerns
- Assign real owners to mitigations
- Look for single points of failure
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 · 67 lines · 42 tokens per session scan A dd0537f15332
premortem is a skill published in the GitHub repository MaxMiksa/Auto-Company (3,156 stars, last pushed 5d ago), licensed MIT. It adds 42 tokens to every session and 521 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
ticket-spec
Turn a raw Linear Triage ticket into a fully specified ai:agent-ready one by exploring the codebase. Use when specifying, refining, or promoting tickets, or when asked why a ticket isn't dispatchable.
hyperframes-cli
Use the HyperFrames CLI development loop: init, add, catalog, capture, lint, check, snapshot, compare, grade-compare, preview, play, present, beats, keyframes, single or batch render, publish, cloud, cloudrun, feedback, lambda, doctor, browser, info, upgrade, skills, compositions, timeline, history, clean, docs…
ciel
Ciel — self-improving, self-researching orchestration intelligence. A living skill graph that routes, acquires, integrates, and evolves capabilities across any skill-aware agent runtime.
design-token-architecture
CIEL's framework for three-layer design token systems (primitive→semantic→component) with CSS variables and naming conventions. Advisory only.
ui_ux_mastery
UI/UX design governance — design systems, accessibility audits, performance budgets, agentic UX patterns.
council_runner
Run Council of Five deliberations — stage orchestration, result aggregation.