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 AcKeskin/contexture --skill pre-pushgit clone --depth 1 https://github.com/AcKeskin/contextureWrote 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/ackeskin/contexture/pre-push)<a href="https://agentmods.dev/skills/ackeskin/contexture/pre-push"><img src="https://agentmods.dev/badge/skills/ackeskin/contexture/pre-push/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/ackeskin/contexture/pre-push"><img src="https://agentmods.dev/badge/skills/ackeskin/contexture/pre-push.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 | $0.00094 | $0.02175 |
| Opus 5.5 | $0.00038 | $0.00870 |
| Sonnet 5.5 | $0.00019 | $0.00435 |
| Haiku 4.5 | $0.00009 | $0.00217 |
Grade A, and why
pre-push 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 1mo 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.
pre-push
Reviewee-side pre-flight before a git push. The first of the GitHub reviewee triad; siblings are pr-author and pr-triage. The reviewer-side counterpart is pr-review.
Whatever the local branch is, that's what ships to the remote. Most pre-push issues are catchable in seconds; none are caught when the push is improvised inline. This skill runs the checklist once, surfaces flags, and stops on a flag — it does not push past a problem on its own.
Triad-wide boundary — no Claude-initiated GitHub writes. Across all three skills, Claude never runs a gh command (or any API call) that writes to GitHub — no gh pr create, no gh pr comment, no thread reply, no gh api POST. Those are drafted and handed to the user to run. Claude does apply local changes (working-tree code edits, staging) and runs read-only gh calls (gh pr view, gh api GET). git push is the one remote-touching action Claude runs — and only the exact push the user asked for, only after the checklist passes — because it ships the user's own commits via git, not via GitHub's API on the user's behalf. The rule: Claude prepares; the user is the one who speaks to GitHub.
Auto-fires via this description, not a hook (per skill-auto-fire (architectural rule)). The right moment is "about to push" — a concept that only exists once a push is imminent, so a SessionStart hook would fire against nothing.
When to run
Auto-fire when:
- About to run a Bash command matching
git push(any form —git push,git push -u origin <b>,git push origin HEAD, etc.). - The user says "push this", "push the branch", "send it up", or equivalent.
Skip when:
- The push target is the user's configured scratch branch (see Configuration). Scratch pushes are intentionally low-ceremony.
- The user explicitly says "skip pre-push", "force push, I know", or similar. Back off; run the push the user asked for.
- This is a re-push in the same session and nothing has changed since the last passing run (don't re-run the full checklist on every push of an unchanged branch — say so and proceed).
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.
- 1mo ago First seen · 99 lines · 94 tokens per session scan A 22ec6574761e
pre-push is a skill published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 2mo ago), licensed MIT. It adds 94 tokens to every session and 2,175 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 2026-09-03.
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.
commit-context
Trace a file, function, or line back to the agent session that produced its current commit. Use when the user asks "why is this code here", "what was the agent doing when this changed", "who wrote this", or wants context on a specific location in the codebase.
commit-history
List recent git commits linked to agent sessions, optionally filtered by branch or repo. Use when the user asks "show agent commits", "what has the agent shipped", "list linked commits", or wants commits with their session context.
git-commit
Analyze changes with Git only and auto-generate conventional commit messages with optional emoji; suggests splitting commits when needed, runs local Git hooks by default (use --no-verify to skip).
feature-publish
Commit the feature, write the PR body, publish in the selected mode, and drive the PR.
release-notes
Draft a release note section from a commit range, grouped by what the reader gets.