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 EZotoff/ez-omo-config --skill wisdom.tmpgit clone --depth 1 https://github.com/EZotoff/ez-omo-configWrote 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/ezotoff/ez-omo-config/wisdom.tmp)<a href="https://agentmods.dev/skills/ezotoff/ez-omo-config/wisdom.tmp"><img src="https://agentmods.dev/badge/skills/ezotoff/ez-omo-config/wisdom.tmp/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/ezotoff/ez-omo-config/wisdom.tmp"><img src="https://agentmods.dev/badge/skills/ezotoff/ez-omo-config/wisdom.tmp.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 | $0.00032 | $0.01823 |
| Opus 5.5 | $0.00013 | $0.00729 |
| Sonnet 5.5 | $0.00006 | $0.00365 |
| Haiku 4.5 | $0.00003 | $0.00182 |
Grade A, and why
wisdom 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 11d 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.
This is a copy
97% identical to wisdom — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wisdom System
You have access to a shared knowledge store called Wisdom — institutional memory that accumulates patterns, gotchas, decisions, and operational facts across sessions. Wisdom is the primary and only runtime memory store. Use it to avoid repeating mistakes, to ground decisions in documented facts, and to reuse proven approaches.
When to Use Wisdom
Search Wisdom (before starting work)
- Before implementing a feature or fixing a bug, search for relevant learnings
- When encountering an unfamiliar error or build failure
- Before making architectural decisions
- When working in an area you haven't touched recently
- For operational queries (deployment paths, config values, infrastructure facts, provider gotchas) — ALWAYS search Wisdom first. Do NOT infer operational facts from code.
Write Wisdom (after discovering something)
- After finding a non-obvious fix or workaround (type:
gotcha) - After establishing a reusable pattern or convention (type:
pattern) - After making an architectural decision with tradeoffs (type:
decision) - After learning a project-specific fact that isn't documented (type:
fact) - After identifying a dangerous pitfall others should avoid (type:
warning)
Commands
Search
~/.sisyphus/scripts/wisdom-search.sh "QUERY" [--scope system|project|plan|all] [--type TYPE] [--limit N] [--json]
--scope: Defaultall. Usesystemfor universal patterns,projectfor project-specific.--type:gotcha,pattern,fact,decision,warning--limit: Default 10--json: Machine-readable output--authority LEVEL: Filter by canonical authority (candidate|verified|published)--status STATUS: Filter by canonical status (active|stale|superseded|retracted)--provenance VALUE: Filter by canonical provenance (closeout|nomination|manual|manifest-import|migration|publish-export|compat-shim)- Default search returns only
activeandstaleentries. - Use
--include-status superseded,retractedto expose hidden lifecycle states when needed. - Access telemetry (
accessed,last_accessed) is updated by default; pass--no-touchfor a strictly read-only search.
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.
- 11d ago First seen · 156 lines · 32 tokens per session scan A 21119c0678a9
wisdom is a skill published in the GitHub repository EZotoff/ez-omo-config (6 stars, last pushed 2d ago), licensed MIT. It adds 32 tokens to every session and 1,823 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 97% identical to wisdom, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
session-flow
Reorient in the current Claude Code session with an evidence-backed map of its goal, pivots, outcomes, current step, and open decisions.
wiki
LLM Wiki — persistent markdown knowledge base that compounds across sessions (Karpathy model).
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
deepnote
DeepNote knowledge base: persistent interlinked markdown wiki with ingest, query, lint, link graph and history.
strategic-compact
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
autopilot
Full autonomous execution from idea to working code.