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.
git clone --depth 1 https://github.com/Amey-Thakur/AI-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/commands/amey-thakur/ai-skills/postmortem-writeup)<a href="https://agentmods.dev/commands/amey-thakur/ai-skills/postmortem-writeup"><img src="https://agentmods.dev/badge/commands/amey-thakur/ai-skills/postmortem-writeup/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/commands/amey-thakur/ai-skills/postmortem-writeup"><img src="https://agentmods.dev/badge/commands/amey-thakur/ai-skills/postmortem-writeup.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 | $0.00020 | $0.00372 |
| Opus 5 | $0.00010 | $0.00186 |
| Sonnet 5 | $0.00004 | $0.00074 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
postmortem-writeup 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.
What it actually says
You were invoked as a slash command. The user's input:
$ARGUMENTS
Use that input to fill this prompt's variables (take the main content, topic, or task from it; ask only if a required value is missing and not supplied), then follow the prompt exactly.
Write a blameless postmortem for:
{incident}
Details: {details}
Structure:
- Summary: what happened, the impact (users, duration, severity), in a few lines a busy reader can grasp.
- Timeline: the sequence from first signal to resolution, with times. Include detection (how we found out) and the key decisions.
- Root cause: the systemic cause, not the person. Use "5 whys" to get past the proximate trigger to why the system allowed it (why did the bad deploy ship, why did the check not catch it, why did the alert not fire).
- What went well and what went poorly: honestly, including detection time and response.
- Action items: specific, owned, and dated changes that prevent recurrence or reduce impact. Each must be concrete ("add a canary check for X"), not aspirational ("be more careful"). Prioritize by impact.
Rules: blameless: focus on systems and processes, never blame individuals (people act reasonably given the information and tools they had). The value is the action items that make the class of failure less likely, so make them real and assignable. Distinguish root cause from trigger. If the timeline or cause has gaps, mark what needs to be confirmed rather than guessing.
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 · 41 lines · 20 tokens per session scan A 72ca6ecca2cc
postmortem-writeup is a command published in the GitHub repository Amey-Thakur/AI-SKILLS (7 stars, last pushed 3d ago), licensed MIT. It adds 20 tokens to every session and 372 once invoked, about $0.0001 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 2026-09-06.
Other commands, from other repositories
feedback-to-closure
Turn raw feedback (reports, Sentry, reviews, QA/audit findings) into deduplicated durable tickets and drive each to production-verified closure.
close
They operate it without you.
burndown-full
Drive a partially-executed plan to 100% coverage across the whole repo — enumerate, batch-execute, prove completeness.
debug-issue
Hypothesis-driven debugging with runtime evidence — Sentry, Firecrawl, and Sequential Thinking, not guessing.
error-plan
Error-handling & observability audit (Sentry + Langfuse) — plan only, no fixes until approved.
stub-plan
Stub / dead-link / fake-component audit + wiring plan — no fixes until approved.