Strands Agents is an open-source SDK for building and running AI agents in Python and TypeScript. Developers use it to create agents with model providers, tools, lifecycle controls, memory, sessions, streaming, tracing, and evaluations, and the catalogue includes add-ons for its agent-building workflow.
Borrowing it
Nothing to install: this file belongs to strands-agents/harness-sdk. 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/strands-agents/harness-sdk/main/.agents/skills/pr-create/SKILL.mdgit clone --depth 1 https://github.com/strands-agents/harness-sdkWrote 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/strands-agents/harness-sdk/pr-create)<a href="https://agentmods.dev/skills/strands-agents/harness-sdk/pr-create"><img src="https://agentmods.dev/badge/skills/strands-agents/harness-sdk/pr-create/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/strands-agents/harness-sdk/pr-create"><img src="https://agentmods.dev/badge/skills/strands-agents/harness-sdk/pr-create.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 | $0.00032 | $0.00571 |
| Opus 5.5 | $0.00013 | $0.00228 |
| Sonnet 5.5 | $0.00006 | $0.00114 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
pr-create 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 2mo 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub PR Create Skill
Process
1. Get the PR Description
- Check for
.local/pr-body.md. If it exists, re-read it fresh and sanity-check that its content matches the current branch's changes (e.g. the description references files, features, or issues consistent with the current diff). If it looks stale or unrelated to the current changes, warn the user and offer to regenerate it. - Else if the user already generated a PR description earlier in the conversation, use that.
- Otherwise, fall back to the
pr-writerskill to generate the title and body.
2. Pre-flight Checks
Check for CONTRIBUTING.md (at the repo root or in docs/) and .github/PULL_REQUEST_TEMPLATE.md. Scan them for any recommended steps before opening a PR — common examples:
- Running a linter or formatter (e.g.
npm run lint,cargo fmt) - Running tests (e.g.
npm test,pytest) - Building the project
- Updating documentation or changelogs
If you find any such steps, list them and ask the user which ones they'd like you to run. Run whichever the user approves. If any step fails, show the output and ask how to proceed before continuing.
If neither file exists or they contain no actionable pre-PR steps, skip this and move on.
To run the local equivalent of the CI merge gate before opening the PR (lint, format, type-check, tests for the areas the change touches), use the pre-push skill — bash .agents/skills/pre-push/run-checks.sh.
3. Push the Branch (if needed)
Check whether the current branch has an upstream tracking branch with all commits pushed. If not, push before creating the PR. If the push fails, show the error and stop.
4. Create the PR
Ensure the final PR body is written to .local/pr-body.md (create .local/ if needed), overwriting any earlier draft. Then create the PR:
gh pr create \
--title "<title>" \
--body-file .local/pr-body.md \
--draft
- Default to
--draft. Only omit it if the user explicitly asks for a non-draft PR. - Do NOT pass
--repo— letghinfer the upstream from the git remotes so the PR targets the correct upstream repository.
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.
- 2mo ago First seen · 52 lines · 32 tokens per session scan A 2e9343b6bbea
pr-create is a skill published in the GitHub repository strands-agents/harness-sdk (8,996 stars, last pushed today), licensed Apache-2.0. It adds 32 tokens to every session and 571 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
apply-patch
Apply multi-file or tricky edits atomically with git apply instead of many fragile editfile calls. Use when changing several files at once or when editfile fails to match.
git-checkpoint
Use git as a safety net - create a checkpoint commit before risky or large changes and roll back cleanly if a change makes things worse. Use before multi-file refactors.
returns-policy
Answer return, refund, and warranty questions for electronics. Use when the user mentions returns, refunds, RMAs, warranty coverage, damaged items, or opened packaging.
technical-troubleshooting
Provide setup, troubleshooting, and maintenance guidance. Use when the user reports a device that won't power on, connectivity issues, setup questions, overheating, or maintenance concerns.
github-triage
Triage GitHub issues through a label-based state machine with interactive grilling sessions. Use when user wants to triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.
release-debrief
Summarises the delta between a tool's latest release and the last summary the user saw. Use when the user asks about what's new, the latest release, release notes, or the changelog of one of the supported tools: Claude Code, OpenCode, llama-swap, or llama.cpp.