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 add-providergit 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/add-provider)<a href="https://agentmods.dev/skills/ezotoff/ez-omo-config/add-provider"><img src="https://agentmods.dev/badge/skills/ezotoff/ez-omo-config/add-provider/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/add-provider"><img src="https://agentmods.dev/badge/skills/ezotoff/ez-omo-config/add-provider.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 | $0.00093 | $0.02383 |
| Opus 5 | $0.00046 | $0.01192 |
| Sonnet 5 | $0.00019 | $0.00477 |
| Haiku 4.5 | $0.00009 | $0.00238 |
Grade A, and why
add-provider 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 4d 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.
- Live catalog: `curl -s <baseURL>/v1/models` (with the provider's auth header) — record exact model ids and advertised context (`n_ctx` where given). How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add / Change Provider or Model
Provider/model edits in this repo have failed nine times in six weeks (Aug 14–30, 2026), each time in one of six predictable ways. This skill is the checklist that makes those failures impossible to ship. Background and full incident corpus: references/rca-2026-08-30.md.
The six failure classes (know them before editing)
| Class | What happened | Anchor |
|---|---|---|
| Missing required fields | model block without limit.output → config rejected at load |
2711fbd |
| Enabled-list omission | provider block added but never added to enabled_providers → invisible |
78687c9→7663dd2 |
| Upstream limit poisoning | config omitted limit.input; models.dev phantom value survived the per-field ?? merge → compaction at 352K/1M |
1776a57 |
| Wrong id / wrong limits | K2.7-era id labeled K3; declared ctx ≠ served ctx; plan-tier ctx < marketing ctx | 8cf88e4, 4c588d0, c53d062 |
| Activation gap | config correct on disk, but TUI panes older than the change kept serving stale config → silent title death for 3 days | Aug 30 title incident |
| Reference drift | model ids referenced in OMO agents / small_model / title that don't resolve, or docs tables lagging config | audit 2026-08-30 |
Coupled surfaces — one change touches up to six places
-
provider.<id>block (ormodelsentry) inconfigs/opencode/opencode.json -
enabled_providersarray (same edit, always) -
~/.local/share/opencode/auth.jsonkey entry (if provider needs a key and it's not inlineoptions.apiKey) - OMO agent/category assignments + fallback chains in
configs/oh-my-openagent/oh-my-openagent.json(if the model gets used there) -
small_model/agent.title.model(only via the promotion rule below) - Docs: README provider table,
docs/configs.mdcounts, MANIFEST.md if artifact inventory changed
Always edit the store path (configs/opencode/opencode.json). The live ~/.config/opencode/opencode.json is a symlink — same file, but edits belong in the repo.
What ships with it
1 file 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.
- 4d ago First seen · 149 lines · 93 tokens per session scan A 4ec2ef72e11b
add-provider is a skill published in the GitHub repository EZotoff/ez-omo-config (6 stars, last pushed 5d ago), licensed MIT. It adds 93 tokens to every session and 2,383 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.
Other skills, from other repositories
trace
Evidence-driven tracing lane that orchestrates competing tracer hypotheses in Claude built-in team mode.
ai-slop-cleaner
Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode.
omc-review
Evaluate finished work for defects, risk, and simplification before it ships.
debug
Diagnose the current OMC session or repo state using logs, traces, state, and focused reproduction.
verify
Verify that a change really works before you claim completion.
omc-doctor
Diagnose and fix oh-my-claudecode installation issues.