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 SethGammon/Citadel --skill postmortemgit clone --depth 1 https://github.com/SethGammon/CitadelWrote 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/sethgammon/citadel/postmortem)<a href="https://agentmods.dev/skills/sethgammon/citadel/postmortem"><img src="https://agentmods.dev/badge/skills/sethgammon/citadel/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.
<a href="https://agentmods.dev/skills/sethgammon/citadel/postmortem"><img src="https://agentmods.dev/badge/skills/sethgammon/citadel/postmortem.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00058 | $0.01635 |
| Opus 5.5 | $0.00023 | $0.00654 |
| Sonnet 5.5 | $0.00012 | $0.00327 |
| Haiku 4.5 | $0.00006 | $0.00163 |
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 1mo 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/postmortem — Campaign Postmortem Generator
Orientation
Use when: A campaign just completed and you want a structured analysis of what broke, what safety systems caught, and what patterns emerged. Also for ad-hoc incident analysis from recent git history.
Don't use when: You want to preserve session context for the next conversation (use /session-handoff), extract reusable patterns from findings into the knowledge base (use /learn), or score and improve quality iteratively (use /improve).
When to Use
- After any Archon campaign completes (Archon should suggest it)
- After a difficult debugging session
- When the user says "what just happened" or "what broke"
- When /do routes "postmortem", "retro", "what broke", "what happened"
Inputs
One of:
- A campaign file path (.planning/campaigns/*.md)
- A time range ("last session", "today", "this week")
- Nothing (reads the most recent completed campaign)
Protocol
Step 1: GATHER
Collect data from all available sources:
From the campaign file (if it exists):
- Direction vs what was actually built (scope drift?)
- Phase completion timeline (which phases needed rework?)
- Decision log entries (what architectural choices were made?)
- Review queue items (what needed human eyes?)
- Circuit breaker activations (what hit the limit?)
- Feature ledger (what shipped?)
From telemetry (.planning/telemetry/):
- hook-timing.jsonl: which hooks fired most, any patterns
- hook-errors.log: what was blocked, what failed, what had parse errors
- Circuit breaker trips
- Quality gate violations
From git history:
- Commits during the campaign period
- Files changed (which areas got the most churn?)
- Any reverts (what was undone?)
- Commit message patterns (fix: commits indicate bugs found)
From the session itself (if no campaign):
- Recent tool calls and their outcomes
- Files edited and errors encountered
Step 2: ANALYZE
Identify patterns across the data:
- What broke: List every failure, error, or unexpected outcome. For each: what happened, what caught it (hook/gate/human/nothing), what it cost (time, rework, tokens).
What ships with it
2 files 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.
- 1mo ago First seen · 191 lines · 58 tokens per session scan A 94add22a2465
postmortem is a skill published in the GitHub repository SethGammon/Citadel (923 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 1,635 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 2026-08-30.
Other skills, from other repositories
zapier-status
Check the health of your Zapier MCP setup. Three modes — health check (dashboard view), audit (find waste and duplicates), diagnose (systematic troubleshooting). Use when asking "is my MCP working?", "check my tools", "audit my setup", "what's broken?", or "zapier status".
audit-project
Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".
root-cause
Find the mechanism behind a failure instead of patching its symptom - reproduce first, one variable per experiment with the prediction written before the run, exit by naming the mechanism and pinning it with a failing test. Use for a bug, an unexplained red test, or a failure that will not reproduce.
discovery
Use this skill when running systematic quality discovery and issue detection. Runs modular probes adapted to the project's tech stack, presents findings interactively for user triage, and creates VCS issues for confirmed problems. Invoked standalone via /discovery or embedded in session-end.
claude-md-drift-check
Use when detecting drift between CLAUDE.md (or AGENTS.md, the Codex CLI alias) / meta narrative and live repository state. Ten checks: absolute-path resolution, 01-projects/ count claims, issue-reference freshness, session-file existence, command-count sync, session-config-parity (mandatory template keys = error…
debug
Use when encountering any bug, test failure, build break, or unexpected behavior — runs a 4-phase systematic debugging process before proposing any fix. Iron Law: NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST. Produces a .orchestrator/debug/ artifact the fixer agent must reference.