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 dcosson/h2 --skill prepare-to-landgit clone --depth 1 https://github.com/dcosson/h2Wrote 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/dcosson/h2/prepare-to-land)<a href="https://agentmods.dev/skills/dcosson/h2/prepare-to-land"><img src="https://agentmods.dev/badge/skills/dcosson/h2/prepare-to-land/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/dcosson/h2/prepare-to-land"><img src="https://agentmods.dev/badge/skills/dcosson/h2/prepare-to-land.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00073 | $0.03628 |
| Opus 5 | $0.00036 | $0.01814 |
| Sonnet 5 | $0.00015 | $0.00726 |
| Haiku 4.5 | $0.00007 | $0.00363 |
Grade A, and why
prepare-to-land 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 9d 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prepare to Land
A long-running work branch — especially one driven by multi-agent work — accumulates artifacts that shouldn't survive into main: closed-but-unfiled beads, accumulated -review.md files, comments tagging which bead/review introduced each line, accidental refactors of test infra/CI/build that weren't the assigned task, expanded sets of make targets where there used to be one. Each of these on its own is small. Together they make the diff to main larger, noisier, and disruptive to other users of the repo.
This skill is the trunk-landing hygiene pass. It does NOT touch the implementation — it cleans up the artifacts and accidental scope that grew around the implementation. Run it after the work is functionally complete and before opening the PR to main.
Scope: specific to the final land into the trunk (main or equivalent). NOT for ordinary feature-to-feature merges that happen along the way (e.g., merging a sub-branch back into the integration branch mid-project). Use it once, at the end, when the work is about to enter shared trunk and become visible to everyone using the repo.
This skill complements plan-work-completion-signoff (which verifies the plan matches the code). prepare-to-land verifies the branch matches the intended scope — the diff doesn't carry artifacts and accidental refactors that other users of the repo shouldn't have to absorb.
Inputs
$0: Work branch name (e.g.,feature/agent-runtime-v2). Default: current branch.$1: Main branch to compare against (e.g.,main). Default:main.
Critical Rules
- Don't change behavior. This skill only deletes/reverts/rewords. If a code change looks like it might be load-bearing, leave it. The bias is conservative — when in doubt, keep.
- Don't touch the merge target. All edits happen on the work branch.
mainis untouched. - Surface scope creep, don't silently undo it. When you find a cross-cutting refactor that wasn't part of the task, propose reverting it AND surface it in the report so the team can decide whether to keep, split out, or drop. Don't unilaterally undo significant changes.
- Run gates before AND after. Confirm
make test/make lint/make typecheck(or the project's equivalents) pass at the start, do the cleanup, confirm they still pass at the end. If any gate breaks, stop and report.
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.
- 9d ago First seen · 248 lines · 73 tokens per session scan A 843543ca6a30
prepare-to-land is a skill published in the GitHub repository dcosson/h2 (159 stars, last pushed 13d ago), licensed MIT. It adds 73 tokens to every session and 3,628 once invoked, about $0.0004 per session on Opus 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 2026-08-30.
Other skills, from other repositories
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.
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
nvca-chart-release
Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.