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/ohm41321/luciazero/retronpx skills add ohm41321/luciazero --skill retrogit clone --depth 1 https://github.com/ohm41321/luciazeroWrote 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/ohm41321/luciazero/retro)<a href="https://agentmods.dev/skills/ohm41321/luciazero/retro"><img src="https://agentmods.dev/badge/skills/ohm41321/luciazero/retro.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 5.1 | $0.00055 | $0.00760 |
| Opus 5 | $0.00028 | $0.00380 |
| Sonnet 5 | $0.00011 | $0.00152 |
| Haiku 4.5 | $0.00006 | $0.00076 |
Grade A, and why
retro 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 5d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retro
Never re-derive a dead end twice. Record only knowledge future work cannot recover cheaply.
1. Scan the session
Ask:
- What took the longest?
- Which attempts failed, and why?
- What plausible approach was wrong?
- What environment/version/flag surprised us?
- What had to be rediscovered?
Also read the discipline report when installed: prefer local
luciazero discipline --project . --json, then the checkout/package CLI.
Use npx only when package resolution is explicitly allowed. A nudge or block
is evidence, not cause; state any diagnosis as likely until repo evidence
confirms it.
2. Filter hard
Keep only what reading the code cannot tell a future agent:
- Null results: measured no gain or broke another property.
- Footguns: an apparently correct action silently breaks something.
- Environment facts, ordering constraints, and why a tempting path is wrong.
Reject diff/history summaries, session-only values, and Anything a grep or
--help answers. If nothing qualifies, stop: an empty retro is a valid result.
3. Route it, then write it
-
Anyone who clones the repo: code/build behavior and disproven approaches. A debugged failure goes to
docs/lessons.md:## <greppable symptom; include exact error string> cause: <root cause> | proven-by: `<command>` | fix: <what fixed it> | date: YYYY-MM-DD -
True in every repository: append one deduplicated line to configured
luciazero-heuristics.mdunder${CLAUDE_CONFIG_DIR:-$HOME/.claude}or${CODEX_HOME:-$HOME/.codex}for the active harness. Never include secrets or personal paths; cap the file at 100 lines and drop the weakest entry when full. -
Only this machine or this user: local paths, versions, preferences, and credential locations must never be committed. Use announced harness memory and update its
MEMORY.mdindex when available. If no memory system exists, keep only a repo-true generalization; otherwise report the lesson without writing it.
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.
- 5d ago First seen · 82 lines · 55 tokens per session scan A 85c06b557b60
retro is a skill published in the GitHub repository ohm41321/luciazero (5 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 760 once invoked, about $0.0003 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
neo4j-agent-memory-skill
Authoritative reference for the neo4j-agent-memory Python package — a graph-native memory system for AI agents built on Neo4j — and for the hosted service (NAMS) at memory.neo4jlabs.com. Use this skill whenever the user mentions neo4j-agent-memory, agent memory with Neo4j, context graphs, the POLE+O model…
tfx-index
프로젝트 구조를 빠르게 파악하거나 토큰을 절약할 때 사용한다. '인덱싱', '프로젝트 구조', '인덱스 만들어', '코드베이스 맵', '프로젝트 개요' 같은 요청에 사용. 새 프로젝트 온보딩, 세션 시작 시 컨텍스트 효율화에 적극 활용.
odin-close-session
Settle a Muninn at the end of a working session. Use when the user says "close out", "wrap up", "settle the base", "we're done here", or invokes the close-session command while working with an Odin knowledge base. Reviews pending candidates, verifies lint, names anything still parked, and (for a git-backed base)…
odin
Organizational memory. Ingest documents into a durable, provenance-tracked knowledge base (a "Muninn") and reason over it. Use when the user says "remember this", "ingest", "odin ...", pastes or points at a document to save, asks to set up a knowledge base, asks what's known across saved sources, or asks Odin to go…
qmd
Search the vault using QMD semantic search. Use PROACTIVELY before reading files. Preference order: (1) MCP tools — mcpqmdquery, mcpqmdget, mcpqmdmultiget, mcpqmdstatus — if they appear in your tool menu, use them first; (2) CLI qmd --index ... as fallback; (3) Grep/Glob only when QMD is not installed. Trigger…
remember
Stores decisions, patterns, and outcomes in the MCP memory knowledge graph as entities with typed observations and relations. Supports recording architectural decisions, anti-patterns, tool preferences, workflow outcomes, and project conventions that persist across sessions. Use when saving patterns, remembering…