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 deciqAI/knowledge-skills --skill premortemgit clone --depth 1 https://github.com/deciqAI/knowledge-skillsWrote 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/deciqai/knowledge-skills/premortem)<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/premortem"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/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/deciqai/knowledge-skills/premortem"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/premortem.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 49 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00111 | $0.01763 |
| Opus 5 | $0.00056 | $0.00881 |
| Sonnet 5 | $0.00022 | $0.00353 |
| Haiku 4.5 | $0.00011 | $0.00176 |
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 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Premortem
Overview
Before committing to a plan, the team imagines that plan has already failed catastrophically, then works backward to enumerate causes. The retrospective frame ("it failed — what caused it?") surfaces risks the prospective frame ("what could go wrong?") systematically misses. Gary Klein operationalized this in HBR (2007), grounded in Mitchell-Russo-Pennington (1989) showing prospective hindsight increases correct failure-mode identification by 30%.
Composes with inversion (premortem is inversion made operational), confirmation-bias (structural counter), hindsight-bias (leveraged as a feature), and critical-thinking.
When to Use
- Before any high-stakes, hard-to-reverse decision (launch, major hire, contract, capital allocation)
- When the team has converged quickly on a single plan with little visible dissent
- When a previous similar effort failed and the team is about to repeat the pattern
- At project milestones to identify emerging failure modes
- Before committing to an AI product launch, model migration, or AI capex/growth spend where model commoditization, inference unit economics, a safety incident, or stretched AI valuations could break the plan within a year
Not when: small reversible decision; equivalent rigorous risk analysis already done; Chaotic domain (action before analysis); time-critical where premortem delays response.
Coaching Novices (Adaptive Front Door)
- Engine mode: user has a concrete decision → run The Process directly.
- Coach mode: user is new → guide step by step.
In Coach mode, respond one step at a time. Each [WAIT] is a hard stop — output only that step's question, then stop.
- One-line: imagine the project already failed — the retrospective frame surfaces risks "what could go wrong?" misses.
- Check fit: if the decision is small and reversible, skip.
- Elicit the specific decision, team, and imagined failure date.
[WAIT — do not advance until user responds]
- Run The Process one step at a time — enforce private generation before group discussion.
[WAIT — do not advance until user responds]
- Close by naming the insight uncovered and scheduling the re-premortem date.
[WAIT — do not advance until user responds]
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 125 lines · 111 tokens per session scan A 227aa37c9f41
premortem is a skill published in the GitHub repository deciqAI/knowledge-skills (10 stars, last pushed 10d ago), licensed MIT. It adds 111 tokens to every session and 1,763 once invoked, about $0.0006 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
superpowers
Runs 14 numbered engineering protocols in one pack — brainstorm, spec, plan, scaffold, TDD red-green-refactor, systematic debugging, refactoring, code review, performance, security, docs, git hygiene, release checklist, postmortem. Use when the user says "build this feature properly", "debug this systematically"…
objection-handler
Turns prospect pushback into progress — diagnoses the real objection behind the stated one and scripts calm, honest responses for price, timing, competitor, authority and brush-off objections. Use when the user says "they said it's too expensive", "prospect went silent", "they're comparing us to X", "how do I answer…
dspy-debugging-observability
Use for debugging DSPy programs, inspecthistory, tracing LLM calls, custom callbacks, observability, monitoring, and cost tracking.
bug-reporting
Load this skill whenever you are filing, reviewing, or generating accessibility bug reports — whether from automated tool output, manual testing, user reports, or testing with disabled people. The purpose of this skill is to make accessibility findings easier to report accurately, connect them to real people and…
upstream-first
Load this skill before implementing a fix for a barrier that may originate in a shared component, design system, renderer, or external dependency rather than this project's own code. Decide whether the responsible fix is local, an existing installed capability, or an upstream contribution before writing a workaround.…
debugging
Investigate and safely fix an active, observable software failure, error, regression, or unexpected behavior using reproduction and evidence. Use for the proximate technical cause and remediation. Do not use for a systemic incident postmortem or general performance tuning without a failure.