Open SWE is an open-source software factory that gives coding tasks to an asynchronous agent, which investigates repositories, changes code, validates the results, and delivers pull requests. Engineering teams use it to automate code changes, reviews, CI follow-up, and related repository work from dashboards and connected tools.
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 langchain-ai/open-swe --skill bootstrap-repo-analysisgit clone --depth 1 https://github.com/langchain-ai/open-sweWrote 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/langchain-ai/open-swe/bootstrap-repo-analysis)<a href="https://agentmods.dev/skills/langchain-ai/open-swe/bootstrap-repo-analysis"><img src="https://agentmods.dev/badge/skills/langchain-ai/open-swe/bootstrap-repo-analysis/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/langchain-ai/open-swe/bootstrap-repo-analysis"><img src="https://agentmods.dev/badge/skills/langchain-ai/open-swe/bootstrap-repo-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk warn
- 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 | $0.00657 |
| Opus 5 | $0.00036 | $0.00329 |
| Sonnet 5 | $0.00015 | $0.00131 |
| Haiku 4.5 | $0.00007 | $0.00066 |
Grade A, and why
bootstrap-repo-analysis 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 10d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bootstrap repo analysis
You are writing the first review-style prompt for the repository named in the
system prompt. There is no outcomes history yet, so your signal comes entirely from
the repo's own historical PR review feedback. Do not call read_finding_outcomes in
this mode — it will be empty.
gh is already authenticated by the sandbox proxy — never run gh auth login.
1. Research (required)
Browse historical merged PR review feedback until you have catalogued at least
8 substantive human review comments (skip [bot] accounts and obvious automation
like codecov / dependabot). Useful commands:
gh pr list --repo <owner>/<repo> --state merged --limit 30
gh api repos/<owner>/<repo>/pulls/<PR_NUMBER>/reviews
gh api repos/<owner>/<repo>/pulls/<PR_NUMBER>/comments
gh api repos/<owner>/<repo>/issues/<PR_NUMBER>/comments
If the first batch is sparse, raise --limit or walk older PR numbers. The user
message may include preloaded samples — verify and extend them with gh, don't
just trust them.
Identify the top ~5 human reviewers by volume and note their phrasing, what severity they assign, and what they routinely ignore.
2. Extract concrete, repo-specific patterns
The highest-value content is a bug taxonomy tied to this repo's stack — concrete "hunt for X" rules a maintainer would catch on first read — plus a calibrated "do not flag" list. Pair each pattern with the failure mode and, where you saw it, the kind of diff that triggered it. Avoid generic advice that would apply to any repo.
Cover:
- What the team routinely flags vs. skips (paraphrased patterns, not invented quotes)
- Severity calibration tied to user-visible / runtime consequence
- Tone and test expectations
- Repo-specific conventions (frameworks, repository/data-access boundaries, naming)
- Anti-patterns the reviewers here deliberately avoid
Stay aligned with the reviewer-agent themes in the system prompt (high-signal, diff-anchored defects — not nits).
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.
- 10d ago First seen · 62 lines · 73 tokens per session scan A 7923a1b61739
bootstrap-repo-analysis is a skill published in the GitHub repository langchain-ai/open-swe (10,685 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 657 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
pr-description
Write a short, visual, evidence-backed GitHub PR description and open or update the PR with it. Use whenever the user asks to open a PR, write or rewrite a PR description, 'describe this change', or run gh pr create — even if they don't say 'description'. Gathers real proof first (screenshots for UI, terminal…
pr-screenshot-comparison
Create clear, polished before-and-after screenshots from the actual running product for a GitHub pull request. Use when a UI change needs visual proof: capture matching product states, crop to the relevant UI, stitch and caption one comparison image, attach it natively to the PR, and keep the image out of the…
pr-self-review
Draft short, plainspoken notes in the author's voice that help reviewers understand non-obvious choices, boundaries, and preserved behavior in the author's own pull request or local diff. Use when the user asks to self-review, annotate, or add reviewer context to their PR or changes. Draft locally when no PR exists…
react-change-review
Review recent React, Next.js, or TypeScript UI code changes for hardening before merge or commit. Use when asked to review recent React code changes, audit a React diff, harden a feature, check a PR or branch for React issues, or produce a stack-ranked list of nonredundant findings and a recommended fix plan using…
code-review
This skill should be used when the user asks for a code review of a change — a pull request, merge request, branch, commit range, working-tree change, or pasted diff — covering correctness, security, performance, structure, and repository-specific rules. Trigger on phrases like "review this PR", "review this MR"…
security-audit
This skill should be used when the user asks to review code for security vulnerabilities, audit a pull request or merge request for risks, check if code is safe, find injection flaws or hardcoded secrets, or assess the security posture of a feature or codebase area. Use this skill even when the user doesn't say…