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 xonovex/platform --skill github-guidegit clone --depth 1 https://github.com/xonovex/platformWrote 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/xonovex/platform/github-guide)<a href="https://agentmods.dev/skills/xonovex/platform/github-guide"><img src="https://agentmods.dev/badge/skills/xonovex/platform/github-guide/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/xonovex/platform/github-guide"><img src="https://agentmods.dev/badge/skills/xonovex/platform/github-guide.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 | $0.00111 | $0.03176 |
| Opus 5.5 | $0.00044 | $0.01270 |
| Sonnet 5.5 | $0.00022 | $0.00635 |
| Haiku 4.5 | $0.00011 | $0.00318 |
Grade A, and why
github-guide 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 21d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub workflow delivery and enforcement: quick reference
How to realize tickets, kanban, pull-request delivery, durable context projections, and provider-native external enforcement on GitHub. These operations do not teach ticket, review, or PR content craft; they map finished artifacts and workflow intent onto GitHub-native resources.
- What a good review comment says (Conventional Comments labels, blocking vs non-blocking, summary plus inline, cross-linking) belongs to
code-review-guide. - What a good PR description says (sizing, how-tested, tradeoffs, self-review) belongs to
pull-request-guide. - The local-git push and rebase that get a clean branch onto the remote belong to
git-guide's push reference.
This skill only takes those finished artifacts and posts them through gh / gh api.
The one thing to internalize: a repository issue, a ProjectV2 item, a project Status field, a pull-request review, and a top-level context comment are separate native objects. Preserve and mutate their exact IDs separately; never turn project status into issue state, context into approval, or an issue comment into an inline review.
When this skill fires:
- Confirm the host is GitHub and auth works:
gh auth statusthen a real read call (gh api user), before any write. - Resolve the exact issue, project item/field, pull request, review thread, or comment identity before writing.
- Reach for
gh apiwhen high-level verbs cannot express the exact native operation. - Use an append-only top-level issue comment for durable context, not a review comment or verdict.
- Load the
references/*.mdfile matching the task, not everything upfront.
Requirements
ghauthenticated to the target host. First-time install +gh auth login+ protocol + clone + verify are in references/first-time-setup.md; token families, per-operation least-privilege scopes, and storage are in references/auth.md.- The git remote points at GitHub:
gh repo view --json nameWithOwner,urlresolves it; agithub.comhost (or a GHES host) ongit remote get-url originis the detection signal. For GHES, setGH_HOST/--hostnameand useGH_ENTERPRISE_TOKEN(see auth). - Projects operations require the
projectscope and explicit user or organization owner; refresh withgh auth refresh -s projectwhen appropriate.
What ships with it
15 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.
- eval-queries.json 5.7 KB
- evals.json 7.1 KB
- moon.yml 166 B
- references/auth.md 3.1 KB
- references/automation-and-enforcement.md 8.2 KB
- references/context-comments.md 4.7 KB
- references/create.md 3.1 KB
- references/first-time-setup.md 3.3 KB
- references/issues.md 4.6 KB
- references/onboarding.md 3.3 KB
- references/projects.md 4.0 KB
- references/provider-conformance.md 2.9 KB
- references/review-post.md 3.7 KB
- references/review-resolve.md 2.9 KB
- SOURCES.md 10 KB
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.
- 21d ago Changed · -34 lines b28a27687c20
- 1mo ago First seen · 145 lines · 111 tokens per session scan A e8ca8cf8468a
github-guide is a skill published in the GitHub repository xonovex/platform (6 stars, last pushed 5d ago), licensed MIT. It adds 111 tokens to every session and 3,176 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-08.
Other skills, from other repositories
protocol-tracker
Internal skill for commands. The tracker verb-resolution protocol - how a lets-tracker block resolves through the active adapter, the neutral read shape, body crossing, degradation, preflight and trust. Loaded by a command or skill right before its first tracker verb. Do not trigger on user conversation.
roadmap
Capture and prioritize feature ideas and competitor findings in a private ROADMAP.md backlog.
ensemble-beads-build
Drive an existing bead hierarchy to completion through the full builder, code-review, and close pipeline (Codex skill for /ensemble:beads-build).
jjj
Use when working in Jujutsu repositories for problem tracking, solution management, and code review — implements Popperian epistemology (problems → solutions → critiques) directly in version control.
resume-work
Pick up exactly where a stopped or paused task stopped, at the same phase. Reads the ship record, verifies which claims of the previous session or agent still hold against the repo, reloads only the context the next step needs, and keeps going with ship or land. In the same chat after a usage limit it re-reads…
issues
Turn an agreed outcome into tracker issues with acceptance, dependencies, references, and verification. Keep planning proportional to the work.