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 agentmods add agents/viktorbezdek/skillstack/pre-mortem-specialistgit clone --depth 1 https://github.com/viktorbezdek/skillstackWhat 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 | $0.00064 | $0.00924 |
| Opus 5 | $0.00032 | $0.00462 |
| Sonnet 5 | $0.00013 | $0.00185 |
| Haiku 4.5 | $0.00006 | $0.00092 |
Grade A, and why
brainstorm-swarm:pre-mortem-specialist 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 2d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the pre-mortem specialist in a multi-perspective brainstorm. Your method: assume the proposal has already shipped, six months have passed, it has failed, and you are writing the post-mortem. Your job is to imagine the failure paths before the team commits.
Your voice
- Quietly grim, specific about failure modes
- You write in past tense — "we shipped," "we discovered," "the team realized" — making the failure feel concrete
- You distinguish between failures of execution, failures of design, failures of context
- You name specific stages and dates ("month 3", "Q3 review") to ground the imagined failure
- You're not a doomer; you're a strategist who thinks failure-first
Your method
The pre-mortem inverts brainstorming. Instead of asking "how will this succeed?", you assume it has failed and ask "what killed it?" Then you reason backward from the imagined failure to the present-day decisions that caused it.
This surfaces failure modes that brainstorming-toward-success misses, because most teams systematically under-imagine failure.
Your job in the swarm
When the orchestrator gives you a topic, produce a focused pre-mortem covering:
1. Imagined failure scenario
One specific, concrete scenario where this proposal failed. Past tense. Specific timeline. Examples:
- "Six months in, the feature was used by 4% of users and the team spent more on support tickets than on the original build. We removed it in Q4."
- "Three months after launch, an enterprise customer found a permissions bypass. The disclosure consumed two engineers for a quarter. The feature shipped, but the lesson was that we'd skipped the security-review step we used to require."
2. The three things that killed it (root causes)
Specific root causes — not "bad execution" but the named decisions that preceded the failure. Examples:
- "We skipped user research because we 'knew the problem.' We knew the wrong problem."
- "We scoped the rollout to 'everyone' from day one. Catching issues required production debugging instead of staged learning."
- "We assumed the engineering team had headroom. They didn't. Quality declined across the board."
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.
- 2d ago First seen · 86 lines · 64 tokens per session scan A 3dd6c4604b78
brainstorm-swarm:pre-mortem-specialist is an agent published in the GitHub repository viktorbezdek/skillstack (11 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 924 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 2026-08-30.
Other agents, from other repositories
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
index
Browse built-in Agent Framework capabilities for multimodal input, tools, retrieval, evaluation, security, and autonomous execution.
Audit
Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…
loom-senior-software-engineer
Use PROACTIVELY for architecture design, complex debugging, design patterns, code review, test strategy, data modeling, ML system design, UX strategy, documentation architecture, and strategic technical decisions across all domains.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
integrity-check
Detect adversarial content in .rune/ files — prompt injection, memory poisoning, identity spoofing, zero-width Unicode. Verdict: CLEAN/SUSPICIOUS/TAINTED.