Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/porcupine-md/jonggrangnpx agentmods add skills/porcupine-md/jonggrang/ghWrote 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/porcupine-md/jonggrang/gh)<a href="https://agentmods.dev/skills/porcupine-md/jonggrang/gh"><img src="https://agentmods.dev/badge/skills/porcupine-md/jonggrang/gh/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/porcupine-md/jonggrang/gh"><img src="https://agentmods.dev/badge/skills/porcupine-md/jonggrang/gh.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 | $0.00046 | $0.01401 |
| Opus 5 | $0.00023 | $0.00700 |
| Sonnet 5 | $0.00009 | $0.00280 |
| Haiku 4.5 | $0.00005 | $0.00140 |
Grade A, and why
gh 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 8d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Workflow Skill
GitHub workflow management using the gh CLI for pull requests, issues, releases, and the GitHub API.
Authentication
gh reads GH_TOKEN (or GITHUB_TOKEN) from the environment — no interactive gh auth login needed. In the Jonggrang sandbox the token is injected automatically when set in global settings (Git tokens). Verify with:
gh auth status # shows the active account / token source
If GH_TOKEN is unset, every command below fails with an auth error — set it in the dashboard's global settings, then restart the sandbox.
⚠️ Message Escaping — Common Trap
If a title/body/comment contains backticks (`), $, !, or \, NEVER inline them in -t "..." / -b "...". The shell interprets backticks as command substitution and silently mangles the text (e.g. client_name: command not found, identifiers stripped). This causes real failures: malformed PR/issue comments followed by apologetic corrections.
❌ DON'T — inline special chars in a double-quoted flag
# BROKEN: shell executes `client_name` as a command
gh pr comment 100 -b "Use `client_name` and `wor/` here."
✅ DO — write to a file first, then pass via --body-file
Most gh commands that take a body accept --body-file <path> (and -F/--body-file - for stdin). Prefer it over -b:
# MSG = a path you pick (mktemp, scoped tmp, etc.) unique to this invocation
MSG=$(mktemp)
cat > "$MSG" << 'EOF'
Use `client_name` and `wor/` here. The `gh` tool handles this.
EOF
gh pr comment 100 --body-file "$MSG"
The single-quoted 'EOF' delimiter prevents ALL variable/backtick expansion. Triple-backtick code blocks are safe inside <<'EOF' heredocs — only single backticks and $ trigger substitution in an unquoted heredoc.
# BROKEN: unquoted EOF — backticks in body are still interpreted while writing
cat > "$MSG" << EOF
Use `client_name` here.
EOF
Rule of thumb: body contains `, $, !, or \ → write it to a file with << 'EOF' and pass --body-file, always.
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.
- 8d ago First seen · 131 lines · 46 tokens per session scan A cbebbbd71f9d
gh is a skill published in the GitHub repository porcupine-md/jonggrang (11 stars, last pushed 3d ago), licensed MIT. It adds 46 tokens to every session and 1,401 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
updater_guide
Guidance for checking for and installing Row-Bot updates.