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 skills/3243dwon/clear-eye/pre-mortemnpx skills add 3243dwon/clear-eye --skill pre-mortemgit clone --depth 1 https://github.com/3243dwon/clear-eyeWhat 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 | $0.00162 | $0.00926 |
| Opus 5 | $0.00081 | $0.00463 |
| Sonnet 5 | $0.00032 | $0.00185 |
| Haiku 4.5 | $0.00016 | $0.00093 |
Grade A, and why
pre-mortem 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-Mortem
A post-mortem asks why something died. A pre-mortem runs it before you commit: imagine the plan has already failed, then reason backward to why. Prospective hindsight makes people name risks they'd otherwise stay politely quiet about.
Core principle
Don't ask "what are the risks?" (vague, easy to wave away). Say "It's six months later and this failed badly. What happened?" — then explain the failure as if it already occurred.
The process
- Fix the plan and a horizon. What's being attempted, and by when do we judge it?
- Declare failure. Vividly: "It's [horizon]. The plan failed. It was a disaster." Sit in that world.
- Generate causes. List the reasons it failed — concrete, specific, in past tense ("the migration corrupted prod data because the dry-run skipped foreign keys"), not abstractions ("poor execution").
- Rank by likelihood × impact. Score each cause on both; sort. The top of that list is where attention belongs.
- Prescribe the one fix that matters most. For the top risks, the single highest-leverage mitigation — and a cheap early-warning signal that tells you it's materializing.
Output format
- The failure scenario — 2–3 vivid sentences, past tense.
- Ranked failure causes — a table or list: cause · likelihood (H/M/L) · impact (H/M/L). Lead with high×high.
- The one fix — the single most leverage-rich mitigation. If you do nothing else, do this.
- Early-warning signals — the cheap canaries that tell you a top risk is happening while there's still time.
- (Optional) Kill criteria — the line that, if crossed, means stop.
Worked example
Plan: Ship a payments rewrite to all users in 6 weeks.
Failure scenario: It's week 7. The cutover dropped ~2% of transactions for three days before anyone noticed; finance can't reconcile, support is on fire, and we've rolled back to a codebase nobody remembers.
Ranked causes:
Cause Likelihood Impact No transaction-level reconciliation between old/new during rollout High High Big-bang cutover instead of % rollout High High Edge-case currencies untested (only USD in staging) Med High On-call didn't know the new system Med Med The one fix: Don't big-bang it. Run new + old in shadow mode reconciling every transaction, then ramp 1% → 100%. This alone defuses the top two risks.
Early-warning signals: Any non-zero reconciliation mismatch in shadow mode; a rise in payment-retry rate; support tickets mentioning "charged twice".
Kill criteria: >0.1% unreconciled at any rollout step → halt and roll back the increment.
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 · 61 lines · 162 tokens per session scan A 191533c53fa0
pre-mortem is a skill published in the GitHub repository 3243dwon/clear-eye (1 stars, last pushed 3mo ago), licensed MIT. It adds 162 tokens to every session and 926 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
thinking-model-router
When unsure which thinking skill fits, map domain and problem type, then return NONE or one primary skill by default (at most three complementary).
thinking-red-team
For authorized security review of code, auth, or APIs you control, model the attacker, map the attack surface, and report only findings with a reproducible exploit path and verified mitigation.
thinking-scientific-method
When a symptom has several plausible causes, rank falsifiable hypotheses and run the cheapest discriminating observation first; prefer least-assumptive survivors only after evidence fit.
thinking-systems
When behavior is emergent across components—fixes elsewhere break, loops/delays dominate—map boundary, stocks/flows, feedback, archetypes, then rank leverage.
thinking-circle-of-competence
Use when a specific claim may lack grounding. Check evidence boundary, size wrongness cost, then answer, fetch, or abstain — never confabulate.
thinking-five-whys-plus
When a fault is localized and the proximate cause is known but the systemic root is not, chain evidence-linked whys with a counterfactual stop and a countermeasure.