Borrowing it
Nothing to install: this file belongs to guillermoscript/lms-front. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/guillermoscript/lms-front/master/.agents/skills/gh-repo-config/SKILL.mdgit clone --depth 1 https://github.com/guillermoscript/lms-frontWrote 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/guillermoscript/lms-front/gh-repo-config)<a href="https://agentmods.dev/skills/guillermoscript/lms-front/gh-repo-config"><img src="https://agentmods.dev/badge/skills/guillermoscript/lms-front/gh-repo-config/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/guillermoscript/lms-front/gh-repo-config"><img src="https://agentmods.dev/badge/skills/guillermoscript/lms-front/gh-repo-config.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00132 | $0.01277 |
| Opus 5 | $0.00066 | $0.00639 |
| Sonnet 5 | $0.00026 | $0.00255 |
| Haiku 4.5 | $0.00013 | $0.00128 |
Grade A, and why
gh-repo-config 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 9d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GH Repo Config — resolve repo facts once, reuse forever
Two kinds of facts feed a GitHub workflow: those discoverable from the repo
and API at runtime (discover fresh, never cache) and those that aren't —
which project board, which Slack channel, who reviews (ask once, cache in
the config file, never ask again). The bundled scripts/config.sh manages
the cache; invoke it by this skill's own path, <skill-dir>/scripts/config.sh.
The config file
<repo-root>/.claude/gh-workflow.config.json — created on first use,
committed or gitignored at the user's discretion (tell them where it is so
they can choose). Example shape; every field is optional and repo-specific:
{
"projectBoard": { "owner": "<github-org-or-user>", "number": 1 },
"slackChannel": "#pr-review",
"slackChannelId": "C0123456789",
"defaultReviewer": { "name": "Alex", "slackId": "U0123456789" },
"prTemplate": ".github/pull_request_template.md",
"branchConvention": "<type>/<N>-<slug>",
"stackSkills": ["vercel-react-best-practices", "vercel-composition-patterns"]
}
Key ownership — which skill consumes what:
| Key | Consumer |
|---|---|
projectBoard |
gh-board |
slackChannel, slackChannelId, defaultReviewer |
ship-pr |
prTemplate |
ship-pr |
branchConvention |
work-issue (branching) |
stackSkills |
work-issue (Step 1 skill loading — chosen once per repo, empty array means "none") |
config.sh commands:
config.sh path Print the config file path (may not exist yet)
config.sh read Print the JSON, or "{}" if none
config.sh get <jq> One value, e.g. config.sh get .projectBoard.number
config.sh init Create it if missing (auto-migrates a legacy
work-issue.config.json if one exists)
Rules:
- If the file already has a value, trust it — don't re-ask or re-detect. If the user says a saved value is wrong mid-run, update the file immediately.
- Batch the questions. When several values are missing, ask about them in one AskUserQuestion call up front, not one at a time deep into a run.
- Write back whatever was resolved (asked or inferred) with
config.sh init+ editing the JSON, and tell the user you saved it and where. - Missing config is not an error. An unconfigured feature (no board, no Slack) means the consuming skill skips that feature and says so.
What ships with it
2 files 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.
- 9d ago First seen · 99 lines · 132 tokens per session scan A 31552743fdce
gh-repo-config is a skill published in the GitHub repository guillermoscript/lms-front (26 stars, last pushed today), licensed MIT. It adds 132 tokens to every session and 1,277 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
gh-issues
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5]…
herdr-kit-workflows
Set up and operate Herdr Kit safely: install and configure the plugin and Mastra Code integration, manage Review and Work repository scope, open primary repository workspaces, synchronize managers, materialize or dematerialize managed worktrees, and update Herdr Kit settings or shortcuts.
herdr-manager-query
Query the authoritative global Herdr Review and Work Manager inventory, recommend actionable PR work, and explicitly materialize confirmed remote-only Review Manager records through the plugin's stable public CLI.
tuturuuu-agent-coordination
Coordinate Tuturuuu shared-worktree ownership, handoffs, and Git commit windows.
summarize-activity
Summarize engineering activity in classroomio/classroomio between two dates — merged PRs, still-open PRs opened in that window, and their demo videos — into a markdown report. Use when the user asks what shipped, what happened, or for a summary/recap/digest of engineering work over a date range.
stage-and-commit
Stage changed files and create a commit following the repo's translation, formatting, and git workflow rules. Use when the user asks to stage, commit, or both.