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/xdido/chiron/postmortemnpx skills add xDido/chiron --skill postmortemgit clone --depth 1 https://github.com/xDido/chironWhat 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 | $0.00058 | $0.03392 |
| Opus 5 | $0.00029 | $0.01696 |
| Sonnet 5 | $0.00012 | $0.00678 |
| Haiku 4.5 | $0.00006 | $0.00339 |
Grade D, and why
postmortem scanned grade D with 2 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
4. **Do not refuse to score** when the user asks for one. If they want a postmortem, score it. **Anti-pattern #2 applies.** Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
1. **Do not moralize.** Grade the work, not the person. *"Loses 2 points for X"* is fine; *"you should really learn Y"* is not. How it starts
The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/postmortem — session-end review and scoring
Step 0 — Load project context
Check if .chiron-context.md exists in the project root. If it exists: read it. DO NOT scan the codebase or read additional files. If not: tell the user: "No project context found. Run /teach-chiron first." Then stop.
Optional user-supplied session summary (or blank):
$ARGUMENTS
CRITICAL — user instructions always win
If the current project's .agents/README.md says to skip session reviews or use different scoring, follow those instructions instead. This command is opt-in.
Current level
Apply the voice level from .chiron-context.md. If missing or unrecognized, use default.
What this command does
Reviews the current GitHub Copilot Agents conversation's recent chiron activity and presents a session-end report. Based on chiron's "After each session" pattern:
- Session summary — 1–2 sentences recapping what was worked on
- Scores —
/10across 5 axes - One thing to practice — concrete, bounded next step
Read-only in v0.3.0. Does NOT write to ~/.chiron/profile.json. Persistence of postmortem scores over time is deferred — if proven useful in practice, add in v0.3.x.
Graceful degradation
If you re-read the recent conversation and find NO recent chiron activity (no /chiron, no /challenge, no /hint, no pervasive-mode chiron behavior signals), respond:
No recent chiron session to review. Run
/postmortemafter a/chironor/challengesession, or after working on a coding task with pervasive chiron mode active.
Stop there. Do not invent a session to review. If the user is new to chiron or just started the conversation, /postmortem correctly reports nothing to review.
If $ARGUMENTS contains a user-supplied summary (e.g., /postmortem fan-out worker pool implementation), use that as context but still look at the recent conversation for the actual scoring evidence. The arguments are a hint about what the user cared about — not a substitute for evidence.
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 First seen · 230 lines · 58 tokens per session scan D 33a528e75fbb
postmortem is a skill published in the GitHub repository xDido/chiron (2 stars, last pushed 4mo ago), licensed MIT. It adds 58 tokens to every session and 3,392 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it D with 2 findings (tells the agent never to refuse, strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
extreme-router-gateway-engine
AI Gateway routing, provider management, and core engine expertise for ExtremeRouter. Use when working on request routing, provider fallback, token refresh, format translation, streaming, or when the user asks about "how does routing work", "add a new provider", "fix the fallback logic", "optimize token usage", or…
extreme-router-refactor
Code refactoring, tech debt cleanup, and code review expertise for ExtremeRouter. Use when cleaning up code, fixing bugs, reviewing PRs, identifying tech debt, or when the user asks to "improve this code", "fix this mess", "why is this broken", "make this cleaner", or mentions code smells, duplication, or poor…
extreme-router-ui-design
UI/UX design and page redesign expertise for ExtremeRouter dashboard. Use when redesigning pages, creating new UI components, improving visual hierarchy, or when the user mentions design, layout, styling, or user experience. Also use when the user asks to "make it look better", "improve the dashboard", "redesign this…
extremerouter-stt
Speech-to-text via ExtremeRouter /v1/audio/transcriptions using OpenAI Whisper / Groq / Gemini / Deepgram / AssemblyAI / NVIDIA / HuggingFace models. Use when the user wants to transcribe audio, convert speech to text, or get subtitles from audio files.
extremerouter-web-search
Web search via ExtremeRouter /v1/search using Tavily / Exa / Brave / Serper / SearXNG / Google PSE / Linkup / SearchAPI / You.com / Perplexity. Use when the user wants to search the web, look up information, find articles, or query a search engine.
extremerouter
Entry point for ExtremeRouter — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch. Use when the user mentions ExtremeRouter, NINEROUTERURL, or wants AI without writing provider boilerplate. This skill covers setup + indexes capability skills; fetch the relevant…