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 patch-opencodegit 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/patch-opencode)<a href="https://agentmods.dev/skills/ezotoff/ez-omo-config/patch-opencode"><img src="https://agentmods.dev/badge/skills/ezotoff/ez-omo-config/patch-opencode/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/patch-opencode"><img src="https://agentmods.dev/badge/skills/ezotoff/ez-omo-config/patch-opencode.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 | $0.00053 | $0.02654 |
| Opus 5.5 | $0.00021 | $0.01062 |
| Sonnet 5.5 | $0.00011 | $0.00531 |
| Haiku 4.5 | $0.00005 | $0.00265 |
Grade A, and why
patch-opencode scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
7. **NEVER** redirect command output into a live runtime artifact (`~/oh-my-openagent-v4.19.2/dist/*`, `~/.opencode/bin/*`, `~/.opencode/plugin/*`, `~/.config/opencode/*` live configs). Diagnostic reads (`git show`, `cat How it starts
The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Patch OpenCode Binary
This skill applies a minimal source fix to the live OpenCode binary. It builds from the exact release tag that matches the running version — never from dev or any other branch.
Pre-flight Checks
Before starting, gather the facts:
# 1. Identify the live version
LIVE_VERSION=$(~/.opencode/bin/opencode --version 2>&1)
echo "Live version: $LIVE_VERSION"
# 2. Identify the source repo
SOURCE_DIR="${OPENCODE_SOURCE:-$HOME/src/opencode}"
cd "$SOURCE_DIR"
# 3. Verify the release tag exists
git tag --list "v${LIVE_VERSION}"
# Expected: v1.17.9 (or whatever the live version is)
# If empty, the version tag doesn't exist — do NOT proceed with dev branch
# 4. Check for running servers
ps -ef | grep 'opencode serve' | grep -v grep
Critical Rules
- NEVER build from
origin/devor any branch other than the release tag - NEVER replace the live binary with a build that reports a different version
- ALWAYS backup the live binary before replacing
- ALWAYS build with
--single --skip-install --skip-embed-web-uifor speed - ALWAYS verify the build version matches the live version before installing
- ALWAYS test the fix on the real surface after installing
- 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,curl) write to.sisyphus/drafts/or a mktemp path ONLY. Live-file writes go through the documented patch flows (timestamped.pre-*backup + verify). 2026-09-08:git show <ref>:dist/index.js > dist/index.jscaptured its own fatal error into the live bundle and killed every fresh session for 4+ hours.
Live Patch Guard contract
The live-patch-guard plugin blocks direct binary swaps (cp/mv/install/dd targeting ~/.opencode/bin/opencode). The supported path is the transactional installer wrapper:
scripts/build-and-install-opencode.sh build
scripts/build-and-install-opencode.sh install <binary>
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.
- 1mo ago Changed · +11 lines 234d23380223
- 1mo ago Changed · +1 lines 0d066f5f0920
- 1mo ago First seen · 231 lines · 53 tokens per session scan A 70644f2f513a
patch-opencode is a skill published in the GitHub repository EZotoff/ez-omo-config (6 stars, last pushed 4d ago), licensed MIT. It adds 53 tokens to every session and 2,654 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.
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.
icode
A Chinese-language, end-to-end coding workflow with separate steps for planning, review, approval, implementation, checking, and final audit. It also includes optional requirement drafting and log-based cause analysis.