Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/EZotoff/ez-omo-confignpx agentmods add skills/ezotoff/ez-omo-config/update-to-latest.tmpWrote 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/update-to-latest.tmp)<a href="https://agentmods.dev/skills/ezotoff/ez-omo-config/update-to-latest.tmp"><img src="https://agentmods.dev/badge/skills/ezotoff/ez-omo-config/update-to-latest.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/update-to-latest.tmp"><img src="https://agentmods.dev/badge/skills/ezotoff/ez-omo-config/update-to-latest.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 | $0.00033 | $0.07276 |
| Opus 5.5 | $0.00013 | $0.02910 |
| Sonnet 5.5 | $0.00007 | $0.01455 |
| Haiku 4.5 | $0.00003 | $0.00728 |
Grade A, and why
update-to-latest scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **NEVER redirect command output into a live runtime artifact** (`~/oh-my-openagent-v4.19.2/dist/*`, `~/.opencode/bin/*`, `~/.opencode/plugin/*`, `~/.config/opencode/*` live configs). Diagnostic reads (`git show`, `cat` This is a copy
94% identical to update-to-latest — 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 — 439 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update to Latest
Role and Purpose
This skill is a guided operational pipeline for future agents, NOT an automatic updater. It analyzes the current state, discovers available updates, produces a recommendation, and only executes after receiving explicit human approval. Future agents invoking this skill must follow every phase in order. No phase may be skipped.
Non-Goals
- This skill does NOT automatically update OpenCode or OMO.
- We do not run package manager or update commands before the approval gate.
- This skill does NOT delete patch registry entries.
- This skill does NOT claim runtime success without evidence.
13 Mandatory Workflow Phases
Phase 1: Preflight / Current-State Inventory
Before any update analysis, capture the complete current state:
- Git cleanliness in the config repo: run
git status --shortand record whether the working tree is clean. - OpenCode version: run
opencode --versionand record the output. - OMO configured source vs runtime source: discover OMO path candidates (see OMO Path Discovery below), then distinguish these evidence levels explicitly:
active_config_registered: a live OpenCode config contains afile://...oh-my-openagentorfile://...oh-my-opencodepath.live_file_installed: that path exists on disk and contains valid OMO source.runtime_loaded: a currently running OpenCode process has actually loaded that path. Do not claim this from config alone. Record the current Git branch, upstream, commit hash, package name/version, and dirty state for every valid local source candidate.
- NPM / package versions: record the installed versions of
opencode-ai,oh-my-opencode, andoh-my-openagentwhere discoverable. - Live symlink targets: verify the four symlinked configs (
opencode.json,oh-my-openagent.json,provider-connect-retry.mjs,retry-errors.json) point into this repo. - Copied plugin / skill / script inventory: list all artifacts installed by
install.shthat are NOT symlinks (e.g. plugins under~/.opencode/plugin/, scripts under~/.opencode/scripts/and~/.sisyphus/scripts/). - Active patch list: run
ls .sisyphus/patches/*.mdand record every patch entry. - Dirty state in OMO source clone: run
git status --shortin the discovered OMO directory.
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 · 439 lines · 33 tokens per session scan A 4ef98580d8eb
update-to-latest is a skill published in the GitHub repository EZotoff/ez-omo-config (6 stars, last pushed 2d ago), licensed MIT. It adds 33 tokens to every session and 7,276 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). It is 94% identical to update-to-latest, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
drydock
Lay the keel of the shipyard harness in any repo — the 4-pillar shared environment (Context, Rules, Tools, Standards), seeded as two faces on day one (CLAUDE.md + GLOSSARY.md) with every other surface appearing on first use, so that every human and agent inherits the same design language and anyone can ship. Run once…
omc-plan
Strategic planning with optional interview workflow.
ralph
Self-referential loop until task completion with configurable verification reviewer.
ask-navigator
Shipyard's navigator — chart a foggy effort (destination unclear, questions not yet stateable) into a map of decision tickets on the repo's issue tracker, then work the frontier one ticket per session until the way is clear, and hand the collapsed decisions to /launch as a mission brief. Wayfinding, not building: it…
project-session-manager
Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions.
ultragoal
Durable multi-goal workflow that persists plan/ledger artifacts under .omc/ultragoal and prints Claude /goal handoff text for the active session.