tmcp-incident-postmortem

tmcp-incident-postmortem is a skill for Claude Code from jakyeamos/tmcp. It costs 36 tokens per session (321 once invoked), scanned A, original, MIT.

A guided workflow for reviewing incidents, such as outages, regressions, or other production failures. It turns evidence about what happened into a postmortem, a written record of the failure and its causes.

In plain words
What is it for?
Building incident timelines, examining root causes and contributing factors, checking the analysis, and planning remediation.
Why use it?
It helps organize scattered logs, timelines, and notes into a consistent analysis with identified evidence gaps and follow-up work.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/tmcp_launcher.mjs review-plan "Create an incident postmortem packet for <project>" --project-path "<project-path>" --evidence-json '<json>' --write.

Part of the tmcp plugin — 20 skills, 1 MCP server shipped together

Good fit Building incident timelines, examining root causes and contributing factors, checking the analysis, and planning remediation.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/jakyeamos/tmcp
agentmods
npx agentmods add skills/jakyeamos/tmcp/tmcp-incident-postmortem

Made for: Claude Code.

Or install tmcp, the plugin that ships this one along with the rest of its 20 skills, 1 MCP server.

Wrote 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.

agentmods badge for tmcp-incident-postmortem

README.md
[![agentmods](https://agentmods.dev/badge/skills/jakyeamos/tmcp/tmcp-incident-postmortem/github.svg)](https://agentmods.dev/skills/jakyeamos/tmcp/tmcp-incident-postmortem)
Your own site
<a href="https://agentmods.dev/skills/jakyeamos/tmcp/tmcp-incident-postmortem"><img src="https://agentmods.dev/badge/skills/jakyeamos/tmcp/tmcp-incident-postmortem/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.

agentmods 80×15 button for tmcp-incident-postmortem

Your own site · 80×15
<a href="https://agentmods.dev/skills/jakyeamos/tmcp/tmcp-incident-postmortem"><img src="https://agentmods.dev/badge/skills/jakyeamos/tmcp/tmcp-incident-postmortem.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 321 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.00321
Opus 5 $0.00018 $0.00161
Sonnet 5 $0.00007 $0.00064
Haiku 4.5 $0.00004 $0.00032

Measured 9d ago against content hash cfcd38d85f28, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

tmcp-incident-postmortem 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 9d 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.

skills/tmcp-incident-postmortem/SKILL.md · 35 lines

What it actually says

TMCP Incident Postmortem

Status: experimental. This workflow remains shipped and callable, but its public contract may change.

Use this skill when the user asks for an incident review, postmortem, outage analysis, regression analysis, root-cause writeup, failure timeline, or follow-up remediation plan.

Use systematic debugging first when the failure has not been reproduced or isolated. Use TMCP after there is enough evidence to turn the event into a durable packet.

Workflow

  1. Gather evidence: observed impact, timeline, logs, commits, CI output, rollback notes, reproduction notes, affected users/systems, and follow-up constraints.
  2. Invoke tmcp_explain for the postmortem packet when available.
  3. Invoke expert_rubric_review_plan for the causal audit and remediation plan.
  4. If MCP tools are unavailable, run from the TMCP plugin root:
node scripts/tmcp_launcher.mjs review-plan "Create an incident postmortem packet for <project>" --project-path "<project-path>" --evidence-json '<json>' --write-artifacts

Output Contract

Produce or cite:

  • TMCP packet and substance_check.
  • Incident timeline and evidence gaps.
  • Root cause and contributing factors.
  • Blast radius and verification gaps.
  • Ordered follow-up remediation plan.
Changes

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.

  1. 9d ago First seen · 35 lines · 36 tokens per session scan A cfcd38d85f28

Subscribe to this mod's changes

tmcp-incident-postmortem is a skill published in the GitHub repository jakyeamos/tmcp (0 stars, last pushed 16d ago), licensed MIT. It adds 36 tokens to every session and 321 once invoked, about $0.0002 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.