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/arch3rpro/dsh-skills/postmortemnpx skills add arch3rPro/dsh-skills --skill postmortemgit clone --depth 1 https://github.com/arch3rPro/dsh-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/arch3rpro/dsh-skills/postmortem)<a href="https://agentmods.dev/skills/arch3rpro/dsh-skills/postmortem"><img src="https://agentmods.dev/badge/skills/arch3rpro/dsh-skills/postmortem.svg" alt="Measured on agentmods" 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 | $0.00075 | $0.00757 |
| Opus 5 | $0.00037 | $0.00378 |
| Sonnet 5 | $0.00015 | $0.00151 |
| Haiku 4.5 | $0.00007 | $0.00076 |
Grade A, and why
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 4d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Postmortem
A postmortem is a backward-looking record of a failure: what broke, the mechanism, why every safety net missed it, and the concrete guardrails added so the same class of bug fails loudly next time. It is the complement of decision-records, which records a forward-looking decision and its alternatives.
The defining constraint: a postmortem is retrospective and failure-specific — it is not an incident log, not a blame report, and not an ADR. Its job is to make the mechanism explicit and to leave guardrails, so the next occurrence fails loudly instead of silently.
When one is owed
Write a postmortem when a bug is:
- Subtle — the mechanism is non-obvious and a careful engineer would re-derive it the hard way;
- Systemic — the reason it escaped every safety net is structural, not a one-line mistake;
- Costly to rediscover — it cost real debugging time, and would cost it again.
A trivial one-line fix with an obvious cause does not earn one. When unsure, ask whether the next engineer would hit the same wall — if yes, write it.
Structure
Open with an Executive summary: one short paragraph a busy reader absorbs in thirty seconds — what broke, the root cause in plain terms, why it escaped, and the durable lesson. Then the detail:
- Summary — what happened, in plain terms.
- Timeline — the sequence that led to the failure and its discovery.
- Root cause — the mechanism, stated precisely, not the nearest symptom.
- Guardrails — the concrete measures added so the same class fails loudly: tests, agent rules, decision records, or process changes. Link each guardrail to the artifact that carries it.
The interesting part is why the process let it through, not the one-line fix. Keep the focus there.
Not a decision record
A postmortem records a failure that already happened; a decision record records a choice you are making now. Do not fold the two: if the postmortem motivates a future decision, record that decision separately in a decision record and cross-link. Keep the retrospective and the forward-looking records distinct.
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.
- 4d ago First seen · 53 lines · 75 tokens per session scan A 7b5766d8a764
postmortem is a skill published in the GitHub repository arch3rPro/dsh-skills (4 stars, last pushed 17d ago), licensed MIT. It adds 75 tokens to every session and 757 once invoked, about $0.0004 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
codex-dsh-orchestrator
Orchestrate bounded Codex-to-DSH collaboration through the existing dshagentlink MCP bridge, including delegation decisions, compact handoff, semantic Flash/Pro/ModLens routing, task follow-up, supervision, and final Codex review. Use whenever the user invokes $codex-dsh-orchestrator, says “请委派给 DSH”, “交给 DSH”, “让…
sol-foreman
Orchestrate quality-first work across native Codex subagents, model-pinned Codex CLI workers, and Claude CLI agents. Use when the user explicitly asks Codex to delegate, parallelize, use agents or subagents, act as a foreman, coordinate a multi-ticket or long-running agent program, recover stalled delegated work…
claude-code-dsh
Delegate bounded work from Claude Code to the user's existing official DSH Web Host while preserving typed supervision, task cursors, follow-up, and safe cancellation.
agency-chief-of-staff
内容优先的复杂项目协调与跨对话生命周期。用于多阶段复杂任务、先讨论需求再执行、根据讨论创建任务执行清单、创建新的 Codex 对话或 Task 执行、跨对话进度管理、角色化团队安排、Codex Thread/Worktree 调度、任务归档、长期知识沉淀、Goal/长期项目及验证审核交付闭环。自然触发包括“这件事比较复杂，先跟我把目标和边界聊清楚，之后再做执行计划”“先讨论需求”“先把需求聊清楚”“根据以上讨论创建执行清单”“整理成任务清单”“开一个新对话执行”“单独创建任务执行”“安排团队来做”“安排几个专业角色”“持续更新进度”“归档任务”“沉淀长期资产”“总结到已有文档”。Pre-read: choose only the…
agency-discuss-plan-execute-progress-archive
Discovery bridge for complex staged projects: discuss goals and boundaries before planning, create an execution checklist, launch a separate task/team, track progress, verify, archive, and retain reusable knowledge. Before any notice, read, lookup, or tool call, choose only the value after = for the user's intent as…
codex-dsh
Delegate bounded work from Codex to the user's existing official DSH Web Host while preserving typed supervision, task cursors, follow-up, and safe cancellation.