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 RobinNorberg/oh-my-copilot --skill omc-gh-triagegit clone --depth 1 https://github.com/RobinNorberg/oh-my-copilotWrote 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/robinnorberg/oh-my-copilot/omc-gh-triage)<a href="https://agentmods.dev/skills/robinnorberg/oh-my-copilot/omc-gh-triage"><img src="https://agentmods.dev/badge/skills/robinnorberg/oh-my-copilot/omc-gh-triage/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/robinnorberg/oh-my-copilot/omc-gh-triage"><img src="https://agentmods.dev/badge/skills/robinnorberg/oh-my-copilot/omc-gh-triage.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 | $0.00113 | $0.01614 |
| Opus 5 | $0.00056 | $0.00807 |
| Sonnet 5 | $0.00023 | $0.00323 |
| Haiku 4.5 | $0.00011 | $0.00161 |
Grade A, and why
omc-gh-triage 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 7d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OMC GitHub Triage
Perform a full GitHub triage cycle for the current project. Reads .omg/config.json for connection settings, queries all relevant GitHub surfaces (issues, PRs, Actions, Dependabot), and presents a prioritized summary with recommended actions.
When this skill is invoked, immediately execute the workflow below. Do not only restate or summarize these instructions back to the user.
Trigger Patterns
- "gh triage"
- "github triage"
- "triage issues"
- "github status"
- "project health"
- "omc-gh-triage"
Step 1: Load Configuration
Read .omg/config.json:
node -e "const f=require('fs');try{process.stdout.write(f.readFileSync('.omg/config.json','utf8'))}catch{console.log('NOT_FOUND')}"
Extract from the github key:
owner— GitHub owner (org or user)repo— repository namedefaultBranch— default branch namelabelTriage— triage label filter (optional)
If config is NOT_FOUND or missing the github key: tell the user to run /oh-my-copilot:omc-gh-setup first and stop.
Step 2: Gather Triage Data
Run all data-gathering queries in parallel (they are independent).
2a. Open Issues Assigned to Me
gh issue list --repo {owner}/{repo} --assignee @me --state open --json number,title,labels,createdAt,milestone --limit 20 2>&1
2b. Untriaged Issues
Issues matching the triage label (if configured) or issues with no labels:
gh issue list --repo {owner}/{repo} --label "{labelTriage}" --state open --json number,title,createdAt --limit 20 2>&1
If labelTriage is not configured, query issues with no labels:
gh issue list --repo {owner}/{repo} --state open --json number,title,labels,createdAt --limit 30 --jq '[.[] | select(.labels | length == 0)]' 2>&1
2c. PRs Needing My Review
gh pr list --repo {owner}/{repo} --search "review-requested:@me" --state open --json number,title,author,createdAt,reviewDecision --limit 20 2>&1
2d. PRs I Authored (status check)
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.
- 7d ago First seen · 184 lines · 113 tokens per session scan A dbe46a73938a
omc-gh-triage is a skill published in the GitHub repository RobinNorberg/oh-my-copilot (5 stars, last pushed 4d ago), licensed MIT. It adds 113 tokens to every session and 1,614 once invoked, about $0.0006 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 2026-09-04.
Other skills, from other repositories
orchestrator-lanes
A file-based project-management playbook for a specific Claude Code development orchestrator. It organizes work into lanes, plans, dependency steps, validation phases, and shipping stages.
project-life
A system for keeping project ideas, tasks, plans, progress, decisions, and lessons in one place. A monorepo-style project workflow is implied, but the input does not define the storage format in full.
lane-contract
A file-based task contract system for describing coding tasks in YAML, including which files a task owns and how it must be checked.
seo-project-life
A guide to the files, commands, stages, and working process of an SEO project. SEO, or search-engine optimization, is the work of improving a site's visibility in search results.
resume-project
A project-resume skill for starting work on an existing repository after a pause or a new session. It reports the current state, blockers, and next actions.
drmax-brandcore
A company facts file and guided process for recording approved claims, products, legal details, and other information that content agents may use. It acts as a single source of truth instead of letting later content generation guess.