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 joao-aires/agent-skills-public --skill postmortem-followupgit clone --depth 1 https://github.com/joao-aires/agent-skills-publicWrote 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/joao-aires/agent-skills-public/postmortem-followup)<a href="https://agentmods.dev/skills/joao-aires/agent-skills-public/postmortem-followup"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/postmortem-followup/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/joao-aires/agent-skills-public/postmortem-followup"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/postmortem-followup.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 | $0.00038 | $0.00700 |
| Opus 5.5 | $0.00015 | $0.00280 |
| Sonnet 5.5 | $0.00008 | $0.00140 |
| Haiku 4.5 | $0.00004 | $0.00070 |
Grade A, and why
postmortem-followup 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 yesterday.
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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Postmortem follow-up
Read composition guidance for optional expertise, fallback and scope.
Start with the supported failure pathway from the incident review. Identify which condition a proposed action changes and why changing it should prevent recurrence, improve detection or reduce harm. This keeps the action tied to the incident's mechanism instead of turning the follow-up into a general backlog of desirable improvements.
Define how the control's effect will be observed before closing the action. Check that it reached the intended target and that the relevant behavior was exercised. If the same failure returns, investigate whether the action was incomplete, undeployed, bypassed, ineffective or based on an assumption that changed. A written, merged or closed action does not settle those questions.
Modes and inputs
- Interactive: help owners choose actions based on the failure pathway and assess whether the proposed control will work.
- Implementation: make a scoped fix, telemetry/test/runbook change or rehearsal tied to an action's success criterion.
- Recurring review: compare action registers, code/config/runtime evidence and new incidents; update existing IDs, flag overdue/unverified controls and prepare bounded improvements. Do not auto-close actions from issue status alone.
Gather reviewed incident evidence, action history, owners, deadlines and applicable implementation scope. Preserve proposed versus accepted ownership and documented exceptions. Consult the follow-up guide for deeper implementation details when needed.
Workflow
- Reconstruct the supported failure and response gaps from the history. Identify unaddressed mechanisms and duplicate/related actions across incidents.
- Propose correction, prevention, detection, mitigation/recovery, evidence-gathering and temporary-control cleanup actions where justified.
- Prioritize by expected harm/risk reduction, recurrence likelihood, response cost, dependencies and implementation effort. Do not invent numeric confidence or savings without a method.
- Define owner, tracking ID, due/review date, affected targets, causal rationale and verification criterion. Replace vague “improve” actions with observable changes/tests.
- Check existing implementation before adding work. Prepare/apply changes within assigned authority using appropriate tests and delivery validation.
- Verify the control on the deployed/intended target: regression/fault test, alert delivery, restore exercise, runbook execution, or observed invariant as applicable.
- Compare new incidents with prior controls: not implemented, not deployed, not exercised, ineffective, bypassed, or changed assumptions are different findings.
- Publish a follow-up report with stable action states and escalation of overdue material risk under local policy.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday Changed · +2 lines 68ec2f219251
- 2d ago Changed · +2 lines 48031420aa5c
- 7d ago First seen · 41 lines · 38 tokens per session scan A ea864776a5ac
postmortem-followup is a skill published in the GitHub repository joao-aires/agent-skills-public (2 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 700 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-15.
Other skills, from other repositories
bug-triage
Re-evaluate open bugs — priority vs severity, assign to sprints, surface systemic trends. Run when the count grows.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
triage-issue-reports
Triage Slack issue reports with one thread-only verdict, evidence review, cause-aware routing, tracker dedupe, and fail-closed ticket creation. Use only from the configured Benny triage automation.
triage-issue
Intelligently triage bug reports and error messages by searching for duplicates in Jira and offering to create new issues or add comments to existing ones. When an agent needs to: (1) Triage a bug report or error message, (2) Check if an issue is a duplicate, (3) Find similar past issues, (4) Create a new bug ticket…
moai-lane-watchdog
One lane stall watchdog iteration: measure lane progress on three channels, classify the stall cause, apply the remedy or resolve the judgment through the decision ladder — instead of waiting on a reply — then record the outcome and report. Reads the unified --auto doctrine at…
investigation
Create an investigation ticket + live-doc for sustained root-cause work (retros, bug archaeology, regression hunts).