Borrowing it
Nothing to install: this file belongs to lolay/nowline. 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/lolay/nowline/main/.claude/skills/steward/SKILL.mdgit clone --depth 1 https://github.com/lolay/nowlineWrote 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/lolay/nowline/steward)<a href="https://agentmods.dev/skills/lolay/nowline/steward"><img src="https://agentmods.dev/badge/skills/lolay/nowline/steward/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/lolay/nowline/steward"><img src="https://agentmods.dev/badge/skills/lolay/nowline/steward.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 | $0.00072 | $0.01642 |
| Opus 5.5 | $0.00029 | $0.00657 |
| Sonnet 5.5 | $0.00014 | $0.00328 |
| Haiku 4.5 | $0.00007 | $0.00164 |
Grade A, and why
steward 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 5d 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.
Steward
How to drive a nowline PR to green. AGENTS.md and specs/ci.md are the background; this file covers the PR loop only and wins over generic PR-driving defaults on conventions.
Most PRs here come from parallel cloud sessions working off the same main, often touching the same specs and man pages within the hour. Most of what goes wrong comes from that.
Before you open a PR
Search open PRs, and anything merged in the last day, for the same change. Three sessions have independently built the same TextMate grammar fix in one evening (lolay/nowline#125, lolay/nowline#130, lolay/nowline#131). If one already covers it, don't open yours: say so to the user. If yours does more, open it and say in the body which PR it overlaps.
Local gate
make pre-commit before every push, and again after any merge from main, because a clean merge can still break a test. A green run from before the merge doesn't count. If the PR touches packages/mcp/, follow it with make pack-mcpb.
Then make changelog-check BASE=origin/main REQUIRE=1, unless the PR is labelled no-changelog.
Don't call pnpm directly to stand in for any of these.
Changelog entries
Write the entry relative to the last release. Before adding a fragment, read the pending ones (make changelog-preview). If your PR changes, replaces or removes behaviour one of them, or a legacy ## [Unreleased] entry, describes, edit or delete that entry instead of adding a contradicting one, and tweaks to a feature that's new since the last release go into its original fragment. v0.9.0 needed lolay/nowline#209 to untangle entries that later PRs had quietly superseded. The rule is in .changelog/README.md.
When merging main in, read the fragments it brings too: a sibling PR may have landed an entry yours now supersedes.
Updating the branch
Keep the branch current. On every wake (CI result, review, conflict notice, check-in), fetch main. If the branch is behind, merge main in, even if the merge is clean. Then run the local gate and push. The merge queue would catch drift anyway, but a current branch surfaces conflicts and man-page stamp breakage while the session that wrote the change is still around to fix it.
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.
- 5d ago Changed · +6 lines 31fcae0e02ed
- 9d ago Changed · +2 lines 3f89ed596ef5
- 16d ago First seen · 63 lines · 72 tokens per session scan A 757b20d61716
steward is a skill published in the GitHub repository lolay/nowline (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 72 tokens to every session and 1,642 once invoked, about $0.0003 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 2026-10-13.
Other skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
github-contributor
A step-by-step guide for contributing code, tests, documentation, or build changes to open-source projects you do not maintain. It explains how to prepare a pull request that follows the project’s rules and is easier for maintainers to review.
hero-diff-highlight
A dark code editor reveals a red deletion then a green addition with a soft pulse. Function: PR / code-change explainer.
git-pr-workflows-git-workflow
Guide changes through code checks, testing, commits, and pull request preparation. Use when coordinating a complete Git workflow and verifying readiness for collaboration.