Borrowing it
Nothing to install: this file belongs to tjmustard/Hypergraph-Coding-Agent-Framework. 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/tjmustard/Hypergraph-Coding-Agent-Framework/main/.agents/skills/hyper-publish/SKILL.mdgit clone --depth 1 https://github.com/tjmustard/Hypergraph-Coding-Agent-FrameworkWrote 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/tjmustard/hypergraph-coding-agent-framework/hyper-publish)<a href="https://agentmods.dev/skills/tjmustard/hypergraph-coding-agent-framework/hyper-publish"><img src="https://agentmods.dev/badge/skills/tjmustard/hypergraph-coding-agent-framework/hyper-publish/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/tjmustard/hypergraph-coding-agent-framework/hyper-publish"><img src="https://agentmods.dev/badge/skills/tjmustard/hypergraph-coding-agent-framework/hyper-publish.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 | $0.00051 | $0.02571 |
| Opus 5.5 | $0.00020 | $0.01028 |
| Sonnet 5.5 | $0.00010 | $0.00514 |
| Haiku 4.5 | $0.00005 | $0.00257 |
Grade A, and why
hyper-publish 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 2mo 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 — 368 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hyper-Publish: Commit, Push, and PR Creation
This enhanced skill automates the full git commit → push → (optional) PR creation workflow with human-in-the-loop (HITL) approval at each critical step.
Key improvements over basic git commit && git push:
- AI-proposes commit message from CHANGELOG
[Unreleased]+ git diff (no typing required) - Timestamps all file mtimes to post-session time
- Displays transparency gate before any changes
- HITL approval gates before each file modification and git command
- Optionally creates a GitHub PR with auto-drafted description
- No system-level approval prompts for git/gh commands (pre-approved via settings.json)
When to use this skill
- After a Claude Code session, when you want to commit changes with an AI-suggested message based on your CHANGELOG
- When you want to commit, push, and optionally create a PR in one unified workflow
- Whenever you run
/hyper-publish [message]or/hyper-publish --dry-run
How to use it
Step 0 — Initialize Permissions (automatic)
Run python .agents/skills/hyper-publish/scripts/setup_permissions.py to patch .claude/settings.json with pre-approved patterns for Bash(git *) and Bash(gh *). This prevents Claude Code from prompting for shell command approval on every invocation.
If settings.json is already configured, this step skips silently.
Step 1 — Parse Arguments
Read the $ARGUMENTS string.
- If it starts with
--dry-run, setDRY_RUN=trueand strip--dry-runfrom the remaining string. - If the remaining string starts with
--skip-pr, setSKIP_PR=trueand strip it. - If remaining string is non-empty, use it as
COMMIT_MESSAGE(skip Step 3 and proceed to Step 4). - If remaining string is empty, proceed to Step 3 (generate message suggestion).
Examples:
/hyper-publish→ Suggest message, offer PR/hyper-publish "Update README"→ Use provided message, offer PR/hyper-publish --dry-run→ Dry-run mode, suggest message/hyper-publish --skip-pr "Release v1.0"→ Use provided message, skip PR step
What ships with it
8 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.
- examples/example_commit_messages.md 3.0 KB
- examples/example_pr_description.md 2.2 KB
- META.yml 310 B
- resources/commit_template.md 1.9 KB
- resources/pr_description_template.md 1.9 KB
- scripts/generate_commit_message.py 8.2 KB runs code
- scripts/generate_pr_description.py 5.2 KB runs code
- scripts/setup_permissions.py 2.6 KB runs code
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.
- 2mo ago First seen · 368 lines · 51 tokens per session scan A 4bb2bc0a3526
hyper-publish is a skill published in the GitHub repository tjmustard/Hypergraph-Coding-Agent-Framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 2,571 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
changelog
Auto-generate a changelog from git commits and sprint data. Internal and player-facing versions.
comet-safe-delivery
A Chinese-language procedure for safely delivering specified Comet changes through Git. It covers checking worktrees and unrelated edits, staging exact files, validating hooks, and authorized commits or pushes.
close-task-commit-push-pr
Close the active backlog task (detected from branch name), commit all changes, push to remote, and open a pull request. Use when the user says "close task and ship it", "close task commit push pr", or invokes /close-task-commit-push-pr.
git-workflow
Guided git workflows: prepare PRs, clean up branches, resolve merge conflicts, handle monorepo tags, squash-and-merge patterns. Use when asked to prepare a PR, clean branches, resolve conflicts, or tag a release.
git-push
A GitHub publishing workflow that handles first-time uploads, routine updates, and tagged releases. Git is a system for recording code changes, while GitHub hosts repositories and releases online.
development-workflow
Detailed development workflow with modular patterns for git, review, testing, and deployment.