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 onsager-ai/dev-skills --skill pre-pushgit clone --depth 1 https://github.com/onsager-ai/dev-skillsWrote 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/onsager-ai/dev-skills/pre-push)<a href="https://agentmods.dev/skills/onsager-ai/dev-skills/pre-push"><img src="https://agentmods.dev/badge/skills/onsager-ai/dev-skills/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/onsager-ai/dev-skills/pre-push"><img src="https://agentmods.dev/badge/skills/onsager-ai/dev-skills/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 | $0.00047 | $0.00849 |
| Opus 5.5 | $0.00019 | $0.00340 |
| Sonnet 5.5 | $0.00009 | $0.00170 |
| Haiku 4.5 | $0.00005 | $0.00085 |
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 15d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-push
Scope
This skill owns integration and publication readiness. AGENTS.md and the repo workflow overlay own workspace isolation, the intended base, gate commands, warning severity and whether a spec link or trivial exception is required. Availability of this skill grants no push, PR or merge authority.
Prerequisites
Inspect branch, worktree and working-tree state before edits. Preserve unrelated changes and keep primary-checkout parking rules intact. Resolve the actual remote and base branch, which may differ from main. Load harness-operations if a tool mapping is needed.
Procedure
- Inspect the current diff and intended base. Refresh that base through the configured remote and record its SHA. If fetching is blocked, report that the base/merge gate could not be verified; do not claim offline integration success.
- Follow the repo's integration route. If its gate builds a committed merge preview itself, satisfy its clean-tree prerequisite and run that gate without replacing it with a manual branch check. Otherwise merge the intended base in the task worktree when required; avoid rewriting published history or forcing a push.
- Resolve conflicts locally. Inventory unresolved paths, reconcile all changed intents, stage resolutions and run relevant gates before completing the merge. Preserve changelog/registry entries from both sides. Regenerate lockfiles and generated assets with their owning tools; do not hand-edit them. For shared documents reconcile section intent. Abort an unsuccessful merge only when it preserves the pre-merge work; never discard unrelated changes.
- Run exactly the repository's mandatory gates and diff-conditional checks on the required tree. Respect its distinction between advisory and blocking warnings. Missing tooling, origin access or environment setup is blocked validation, not a pass. Do not suppress failures, weaken assertions or bypass hooks. Once the required checks pass, repeat them only for changed inputs, a new failure or an unresolved concern. Missing optional tooling does not block independent work or reviewable PR preparation; describe its validation limit.
- Apply the declared contribution process. Where SDD is required, verify a spec exists, its blocking decisions are resolved, and the proposed PR links the right delivery slice. Use issue-spec for missing specs. Where a trivial exception is allowed, justify it using the repo's definition. Reconcile issue references in commits deliberately; incidental mentions do not imply closure. A repository without this gate acquires none from this skill.
- When publication is authorized, publish the validated branch with the available Git transport or connected GitHub API. On transport failure use an available authenticated equivalent; when publishing trees through an API, preserve modes, deletions and parent lineage and verify exact tree identity. Do not force-update a protected/long-lived branch. Limited retries are appropriate for transient errors; authorization errors require capability diagnosis, not repeated retries.
- Hand PR creation/update and its check sweep to pr-lifecycle.
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.
- 15d ago Changed · +3 lines f2371605bc3c
- 18d ago Changed · -60 lines · -120 tokens per session fb5831be5f4c
- 1mo ago First seen · 128 lines · 167 tokens per session scan A f4e44b5d1e1b
pre-push is a skill published in the GitHub repository onsager-ai/dev-skills (7 stars, last pushed 3d ago), licensed MIT. It adds 47 tokens to every session and 849 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
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.