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 0xDarkMatter/claude-mods --skill push-preflightgit clone --depth 1 https://github.com/0xDarkMatter/claude-modsWrote 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/0xdarkmatter/claude-mods/push-preflight)<a href="https://agentmods.dev/skills/0xdarkmatter/claude-mods/push-preflight"><img src="https://agentmods.dev/badge/skills/0xdarkmatter/claude-mods/push-preflight/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/0xdarkmatter/claude-mods/push-preflight"><img src="https://agentmods.dev/badge/skills/0xdarkmatter/claude-mods/push-preflight.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 | $0.00101 | $0.02281 |
| Opus 5.5 | $0.00040 | $0.00912 |
| Sonnet 5.5 | $0.00020 | $0.00456 |
| Haiku 4.5 | $0.00010 | $0.00228 |
Grade A, and why
push-preflight 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 11d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Push Preflight
Formalised pre-push safety check. Runs before every git push <remote> where the remote is not a local file path. Refuses on secret hits; warns on size/forbidden-file; confirms intent before pushing.
Use this skill whenever the user asks to push, or before Claude runs git push to any remote. Complements git-ops (which handles the push itself) — this is the gate that runs immediately before.
Why the name. Formerly push-gate. It runs six checks (secret scan, clean tree, forbidden files, fast-forward, size advisory, open-issue advisory), so secret-scan would undersell it, and mislead: it scans only the commits being pushed, never history (that is security-ops). The name matches scripts/preflight.sh. The secret scan leads the description because the description, not the name, is what selects the skill.
Hard rules
- Gitleaks is a required dependency. If not installed, emit the install instructions and refuse. Do not silently fall back to regex-only.
- Any secret-scanner hit ⇒ refuse. No bypass flag. Confirmed-safe findings go into the committed repo-local allowlists (
.gitleaksignorefor gitleaks,.push-preflight-allowfor the regex layer — see §False-positive handling), never an inline override. Real secrets force the user to rewrite history and re-invoke the gate. - Never
--forcepush. The gate never passes a force flag. If the user needs to force-push, that's a separate conversation with explicit authorization. - Never
--no-verify. Don't skip hooks. - Working tree must be clean. Refuse on dirty tree (uncommitted work could be accidentally stashed into the push flow).
- Remote must be named. Refuse if
git pushis called without an explicit remote and branch.
Workflow
Step 1 → Identify remote + branch
Step 2 → git fetch <remote>
Step 3 → Verify working tree clean
Step 4 → Compute pending commits (count + list)
Step 5 → Check divergence (non-ff ⇒ require user to rebase first)
Step 6 → Secret scan ────────┐ gitleaks honours .gitleaksignore,
│ regex layer honours .push-preflight-allow
Step 7 → Forbidden-file scan │ refuse on any hit
Step 8 → Size advisory │
→ Open-issue advisory (github-ops; informational, never gates)
Step 9 → Explicit confirm │
Step 10 → git push <remote> <branch>
Step 11 → Post-push verify (ls-remote matches pushed SHA)
What ships with it
5 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.
- 11d ago First seen · 139 lines · 101 tokens per session scan A c72b42de92eb
push-preflight is a skill published in the GitHub repository 0xDarkMatter/claude-mods (68 stars, last pushed 4d ago), licensed MIT. It adds 101 tokens to every session and 2,281 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 2026-10-08.
Other skills, from other repositories
core-workflow
Detailed development workflow patterns, checklists, and standards. Auto-loads for complex tasks, planning, debugging, or when explicit patterns are needed. Contains session protocols, git conventions, security checklists, review-based validation, and communication standards.
ship
Commit, push, create PR(s), and auto-finalize — full automation pipeline. Handles uncommitted changes and recently created PRs.
git-flow-next
Use git-flow-next with develop as the default and main as production. Branch feature work from develop, prepare releases there, promote them to main after session PRs merge, and carry hotfix branches to both branches through PRs.
troubleshoot-precommit
Troubleshoot pre-commit hook failures and auto-fixes.
git-workflow
Skill "git-workflow" from halflength-ampleness75/claude-code-recipes, covering git workflow, branch naming, rules, conventional commits and format.
commitkit
Commit this session's changes with Conventional Commits messages derived from the actual diff, then push them to origin. Use when the user asks to commit changes, says "commit this", runs "/commitkit", runs "/commitkit all" to commit every change in the tree, or wants a well-formed commit message written for staged…