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.
npx skills add saemihemma/lead-producer-oss --skill workflow-premortemgit clone --depth 1 https://github.com/saemihemma/lead-producer-ossWrote 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/saemihemma/lead-producer-oss/workflow-premortem)<a href="https://agentmods.dev/skills/saemihemma/lead-producer-oss/workflow-premortem"><img src="https://agentmods.dev/badge/skills/saemihemma/lead-producer-oss/workflow-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/saemihemma/lead-producer-oss/workflow-premortem"><img src="https://agentmods.dev/badge/skills/saemihemma/lead-producer-oss/workflow-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 | $0.00060 | $0.01032 |
| Opus 5 | $0.00030 | $0.00516 |
| Sonnet 5 | $0.00012 | $0.00206 |
| Haiku 4.5 | $0.00006 | $0.00103 |
Grade A, and why
workflow-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 8d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-Mortem Workflow
Purpose
Surface failure modes of a high-stakes decision before commit by imagining it has already failed and reasoning backward. Produces a durable pre-mortem artifact: failure stories ranked by likelihood and impact, each with a leading indicator, a mitigation or kill-criterion, and an owner.
Use When
- Decision is hard-to-reverse, launch-critical, or high-blast-radius
- A go/no-go or irreversible commit is imminent and failure would be costly
- Lead Producer's inline lightweight pre-mortem surfaced failure stories too heavy to resolve in a few lines
- User explicitly asks for a pre-mortem
Do NOT Use When
- Decision is cheaply reversible or low blast radius -> use the inline lightweight pre-mortem in the Devil's Advocate Protocol
- Something is already broken in production ->
workflow-incident-response - Root cause of an existing failure is unknown ->
workflow-systematic-debugging - The task is iterating the quality of an existing artifact, not foreseeing a decision's failure ->
workflow-specialist-hardening - No concrete decision exists yet, only broad unknowns ->
workflow-project-discovery
Working Method
Phase 1: Frame the Decision
- State the decision in one sentence and the commit point: what becomes hard to undo, and when.
- Define "failure": the observable outcomes that would make this decision a clear mistake.
- Set the horizon (e.g. "3 months after launch") so failure stories are concrete.
Phase 2: Generate Failure Stories
- Assume the decision has already failed at the horizon. Generate distinct failure stories, narrating each backward from the failed end-state to its root cause.
- Pull domain-specific failure modes from relevant specialist perspectives by routing through LP. Do not invent reviewers.
- Separate confirmed risk from hypothesis. Prefix material unverified assumptions with
UNCONFIRMED:.
Phase 3: Rank & Convert
- Rank failure stories by likelihood (high/medium/low) and impact (high/medium/low).
- For each story, define a leading indicator: the earliest observable signal that this failure is beginning.
- For each story, define a mitigation or kill-criterion and assign an owner.
- Drop stories that have no plausible mechanism. Do not pad the list for volume.
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.
- 8d ago First seen · 79 lines · 60 tokens per session scan A 6187abcd2200
workflow-premortem is a skill published in the GitHub repository saemihemma/lead-producer-oss (2 stars, last pushed 8d ago), licensed MIT. It adds 60 tokens to every session and 1,032 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…