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 agentmods add skills/harnessprotocol/harness-kit/merge-prnpx skills add harnessprotocol/harness-kit --skill merge-prgit clone --depth 1 https://github.com/harnessprotocol/harness-kitWrote 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/harnessprotocol/harness-kit/merge-pr)<a href="https://agentmods.dev/skills/harnessprotocol/harness-kit/merge-pr"><img src="https://agentmods.dev/badge/skills/harnessprotocol/harness-kit/merge-pr.svg" alt="Measured on agentmods" 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 | $0.00098 | $0.00910 |
| Opus 5 | $0.00049 | $0.00455 |
| Sonnet 5 | $0.00020 | $0.00182 |
| Haiku 4.5 | $0.00010 | $0.00091 |
Grade A, and why
merge-pr 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 4d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Merge PR
Takes a ready PR and lands it: verify → sync → confirm → squash merge → cleanup.
Announce at start: "I'm using the merge-pr skill to merge this PR."
Step 1: Identify the PR
Check for an open PR on the current branch, or use a user-specified PR number:
# Current branch
gh pr view --json number,title,url,state,baseRefName,headRefName 2>/dev/null
# Or if user specified #N:
gh pr view <N> --json number,title,url,state,baseRefName,headRefName
No PR found: Stop and redirect:
"No open PR found on this branch. Use
/open-prto create one first."
PR found: Note the PR number, title, base branch, and URL. Continue.
Step 2: Verify Readiness
Check CI status and review state:
gh pr checks <N>
gh pr view <N> --json reviews --jq '.reviews[] | select(.state == "CHANGES_REQUESTED")'
CI failing: Stop and report which checks are failing. Do not merge.
"CI is failing on [check names]. Fix these before merging, or use
/open-prto address them."
CHANGES_REQUESTED review: Stop and report who requested changes.
"PR has CHANGES_REQUESTED from [reviewer]. Resolve this before merging."
All clear: Continue.
Step 3: Base Branch Sync
Check whether the base branch has moved since branching:
BASE=$(gh pr view <N> --json baseRefName --jq '.baseRefName')
git fetch origin $BASE
git log HEAD..origin/$BASE --oneline
New commits exist: Rebase and force-push:
git rebase origin/$BASE
git push --force-with-lease
If rebase has conflicts, resolve them, then git rebase --continue. After force-push, re-verify CI passes before continuing.
No new commits: Skip.
Step 4: Confirm with User
Before merging, confirm:
Ready to squash merge PR #<N> ("<title>") into <base>.
All checks passed. Proceed?
Wait for confirmation. If the user says to always proceed without asking (e.g. "auto-merge", "no need to confirm"), skip this prompt for the rest of the session.
What ships with it
1 file 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.
- 4d ago First seen · 131 lines · 98 tokens per session scan A f940df5d5554
merge-pr is a skill published in the GitHub repository harnessprotocol/harness-kit (10 stars, last pushed today), licensed Apache-2.0. It adds 98 tokens to every session and 910 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
llm-wiki
Build and maintain an LLM-curated personal knowledge base — the "LLM Wiki" pattern from Andrej Karpathy's April 2026 gist. Use this skill whenever the user wants to ingest a source (paper, article, transcript, PDF, notes) into a persistent compounding knowledge base, ask a question against accumulated notes, lint or…
studio
Architecture Studio control plane — initialize or inspect a studio workspace, create and register projects, or route an architecture/AEC task to the right agent or skill. Use when the user runs /as:studio, asks to set up or open their studio, manage its projects, or describes a task without naming a skill.
product-image-processor
Download, resize, and remove backgrounds from product images at scale. Use when the user asks to "process product images", batch-download images from the schedule, strip backgrounds, or standardize product photos.
tool-catalog
Show the available Architecture Studio skills and their host-appropriate commands, plus Claude Code's native Architecture Studio agents. Use when the user invokes tool-catalog, asks "what can you do" or "what skills are available", or wants a directory of plugin commands. Do not use for a host's native skill-list…
cesiumjs-imagery
CesiumJS imagery layers - ImageryProvider, ImageryLayer, ImageryLayerCollection, WMS, WMTS, Bing, OpenStreetMap, ArcGIS, Mapbox, tile discard policies. Use when adding or swapping base map layers, configuring imagery providers, layering multiple map sources, or creating split-screen imagery comparisons.
studio-feedback
Prepare a user-reviewed Architecture Studio bug report or feature request for GitHub. Use when the user runs /as:studio-feedback, says "report a bug", "this skill broke", "send feedback", or requests a feature. Do not use for Claude Code's native /feedback command.