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 sjarmak/coding-agent-workflows --skill premortemgit clone --depth 1 https://github.com/sjarmak/coding-agent-workflowsWrote 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/sjarmak/coding-agent-workflows/premortem)<a href="https://agentmods.dev/skills/sjarmak/coding-agent-workflows/premortem"><img src="https://agentmods.dev/badge/skills/sjarmak/coding-agent-workflows/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/sjarmak/coding-agent-workflows/premortem"><img src="https://agentmods.dev/badge/skills/sjarmak/coding-agent-workflows/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 | $0.00040 | $0.01696 |
| Opus 5.5 | $0.00016 | $0.00678 |
| Sonnet 5.5 | $0.00008 | $0.00339 |
| Haiku 4.5 | $0.00004 | $0.00170 |
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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Premortem: Prospective Failure Narratives
Spawn N independent agents, each writing a narrative from the future where the project FAILED for a different root cause. No agent sees others' failure stories. A lead agent then synthesizes the narratives into a structured risk registry with severity ratings and mitigations.
Based on Gary Klein's premortem technique: "prospective hindsight", imagining an event has already occurred, increases the ability to identify reasons for future outcomes by ~30%. Starting from "it failed" bypasses the planning fallacy and optimism bias that normally prevent teams from envisioning failure modes.
Arguments
[N] [path/to/design.md | inline description]
- N is the number of failure lenses (default 5, min 3, max 7).
- Input is a design doc, architecture doc, PRD, or project plan, or an inline description. Missing or unclear: ask the user to clarify before starting.
Phase 1: Frame the Project
If a file path is given: read it and extract the key design decisions, architecture, dependencies, and assumptions.
If inline: parse the project description.
Prepare a project brief that includes:
- What is being built
- Key technical decisions
- Dependencies (internal and external)
- Timeline constraints
- Team context (if available)
- Critical assumptions
Present the project brief to the user and confirm before proceeding. Adjust if the user gives feedback.
Phase 2: Spawn Failure Agents
Launch all N agents in parallel using the Agent tool. Each agent gets the same project brief and a unique failure lens: a category of failure they must explore.
Standard Failure Lenses
Select N from the following (always include lenses 1-3, then fill remaining slots in order):
- Technical Architecture Failure: the core technical approach was wrong (scaling limits, fundamental design flaw, performance cliff, wrong data model)
- Integration & Dependency Failure: external dependencies failed or changed (API deprecation, library vulnerability, vendor shutdown, incompatible upgrade)
- Operational Failure: the system works in dev but fails in production (deployment complexity, monitoring gaps, incident response blind spots, data migration corruption)
- Scope & Requirements Failure: we built the wrong thing (misunderstood requirements, missed stakeholder needs, wrong assumptions about user behavior)
- Team & Process Failure: the people-side failed (knowledge silos, handoff gaps, testing shortcuts, documentation debt)
- Security & Compliance Failure: security breach, data leak, regulatory violation, access control gap
- Scale & Evolution Failure: works at current scale but breaks at 10x (database bottleneck, cost explosion, architectural ceiling)
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 · 172 lines · 40 tokens per session scan A 3aa340df5765
premortem is a skill published in the GitHub repository sjarmak/coding-agent-workflows (6 stars, last pushed 17d ago), licensed MIT. It adds 40 tokens to every session and 1,696 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 2026-08-31.
Other skills, from other repositories
browser-trace
Capture a full DevTools-protocol trace of any browser automation — CDP firehose, screenshots, and DOM dumps — then bisect the stream into per-page searchable buckets. Use when the user wants to debug a failed run, audit network/console/DOM activity, attach a trace to an in-progress session, or feed structured per-page…
planning-with-files
Persistent file-based planning for multi-step AI-agent work. Keeps taskplan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected project planning context. Automatic recovery reads project planning files only. Explicit session-catchup.py --metadata reads same-project local agent session records and…
ai-elements
Build AI chat interfaces using ai-elements components — conversations, messages, tool displays, prompt inputs, and more. Use when the user wants to build a chatbot, AI assistant UI, or any AI-powered chat interface.
exa-search
Use Exa MCP for current web, code/docs, company, people, and page-fetch research. Prefer current hosted tool schemas and note deprecated tools.
ontoly-software-graph
Use Ontoly's deterministic Software Graph and MCP capabilities for repository architecture, request tracing, dependency analysis, configuration lookup, and impact analysis before falling back to source search.
kimi-webbridge
A way for an AI agent to control the user's real web browser, including pages where the user is already signed in. It can navigate, click, type, read page content, and take screenshots.