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 rockscy/solo-skills --skill postmortem-sologit clone --depth 1 https://github.com/rockscy/solo-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/rockscy/solo-skills/postmortem-solo)<a href="https://agentmods.dev/skills/rockscy/solo-skills/postmortem-solo"><img src="https://agentmods.dev/badge/skills/rockscy/solo-skills/postmortem-solo/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/rockscy/solo-skills/postmortem-solo"><img src="https://agentmods.dev/badge/skills/rockscy/solo-skills/postmortem-solo.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 | $0.00068 | $0.01649 |
| Opus 5 | $0.00034 | $0.00825 |
| Sonnet 5 | $0.00014 | $0.00330 |
| Haiku 4.5 | $0.00007 | $0.00165 |
Grade A, and why
postmortem-solo 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 10d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Postmortem Solo / 单兵复盘
When to use
- Something didn't go to plan in the last 30 days: outage, failed launch, missed deadline, customer churn spike, broken release.
- The user is the only person responsible — there's no team to interview.
- The goal is one or two concrete changes, not a 10-page report.
When NOT to use
- The incident is still active — fix it first, postmortem after.
- The user wants emotional processing, not a postmortem. Suggest a walk or a friend; this skill is for cold analysis.
- It's a routine setback (one bug in production, one slow week) — not every bump needs a postmortem.
Structure
Five sections, strict word limits:
- What happened — 3 bullets, factual, no analysis. (≤ 60 words)
- Impact — what did the failure cost? Users affected, revenue lost, hours sunk, reputation hit. (≤ 40 words)
- Timeline — bullet list with timestamps if known: trigger → detection → response → resolution. (≤ 100 words)
- Root cause(s) — apply 5 Whys but stop the moment you hit a systemic cause (process, default, missing tool), not a personal one ("I was tired"). (≤ 80 words)
- Changes — at most 2 concrete changes with owner (you), due date, and verification method. (≤ 60 words)
Total: ≤ 350 words. If you need more, you're hiding from a decision.
The "no blame, but yes accountability" rule
Solo postmortems have a trap: you're the only person who could have caused this, so it's tempting to either (a) flagellate yourself, or (b) blame externalities ("Stripe was flaky"). Neither is useful.
Correct framing: "What system / habit / default could I change so that next-month-me cannot make this mistake even if next-month-me is tired and distracted?"
This forces solutions toward process, automation, or alarms — not "be more careful next time."
Output format
# Postmortem: <one-sentence headline>
**Date:** <YYYY-MM-DD> — drafted <X> days after the incident.
## What happened
- …
- …
- …
## Impact
…
## Timeline
- HH:MM — <event>
- HH:MM — <event>
## Root cause(s)
…
## Changes
1. <change> — owner: me, due: <date>, verified by: <how I'll know it worked>
2. <change> — owner: me, due: <date>, verified by: <how>
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.
- 10d ago First seen · 146 lines · 68 tokens per session scan A 5b47782179fa
postmortem-solo is a skill published in the GitHub repository rockscy/solo-skills (8 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 1,649 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 2026-08-31.
Other skills, from other repositories
error-translator
A Chinese-language assistant that translates English programming errors and explains what they mean. It covers common errors from languages and frameworks including Python, JavaScript, TypeScript, Java, and others.
eslint-fix
A project-aware assistant for finding and fixing ESLint errors, warnings, and configuration compatibility problems. ESLint is a tool that checks JavaScript and TypeScript code for style and common mistakes.
perf-profiler
A performance investigation guide that uses repeatable measurements and profiling evidence to find where software spends time or resources. Profiling records runtime activity such as CPU use, memory use, database work, or network delays.
log-analyzer
A log-analysis helper that reads application and system logs to find unusual patterns and likely causes. Logs are records of events such as errors, requests, warnings, and service activity.
customer-escalation
Package an escalation for engineering, product, or leadership with full context. Use when a bug needs engineering attention beyond normal support, multiple customers report the same issue, a customer is threatening to churn, or an issue has sat unresolved past its SLA.
tool-calling-tutor
Use when a tool-calling agent does not call a tool, sends wrong arguments, loops without stopping, or needs a function schema. Guides a four-branch diagnosis and five-step schema repair. Do not use for framework-specific, MCP-server, or production-observability questions.