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.
Borrowing it
Nothing to install: this file belongs to langchain-ai/open-swe. 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/langchain-ai/open-swe/main/.github/prompts/fix_preview_typecheck.mdgit 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/commands/langchain-ai/open-swe/fix_preview_typecheck)<a href="https://agentmods.dev/commands/langchain-ai/open-swe/fix_preview_typecheck"><img src="https://agentmods.dev/badge/commands/langchain-ai/open-swe/fix_preview_typecheck/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/commands/langchain-ai/open-swe/fix_preview_typecheck"><img src="https://agentmods.dev/badge/commands/langchain-ai/open-swe/fix_preview_typecheck.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 | $0.00000 | $0.00199 |
| Opus 5.5 | $0.00000 | $0.00080 |
| Sonnet 5.5 | $0.00000 | $0.00040 |
| Haiku 4.5 | $0.00000 | $0.00020 |
Grade A, and why
fix_preview_typecheck 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 yesterday.
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.
What it actually says
This checkout is the preview deployment being assembled: main plus every labelled pull request, merged together.
The combined tree fails the dashboard typecheck, and stdin holds the failing command and its output.
Earlier conflict resolutions in this tree may be wrong, such as an import that points at a module that no longer exists.
Fix the errors so the result behaves the way every merged pull request intended, then commit the fix on HEAD.
Change only what the errors require.
Do not revert a pull request's change to make the errors go away.
Whatever is committed on HEAD when you finish is what deploys.
Do not run the typecheck, package scripts, or anything else from this tree: this checkout holds a write credential, and the build typechecks your commit itself, in isolation, once you finish.
Finish with cli_result: exit_code 0 if you committed a fix, 1 otherwise, and a one-sentence stdout saying what you changed.
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.
- yesterday Changed · +5 lines 28e8376450d2
- 23d ago First seen · 8 lines · 0 tokens per session scan A 760a73f24e98
fix_preview_typecheck is a command published in the GitHub repository langchain-ai/open-swe (11,133 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 199 tokens. 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 2026-10-06.
Other commands, from other repositories
t00-git
A Git assistant that explains version-control commands and guides work with commits, branches, merges, pull requests, and conflicts. Git records code changes so developers can review, restore, and share versions.
caveman-commit
Generate a terse caveman-style commit message for staged changes.
commit
A command that examines staged Git changes and proposes a commit message using the Conventional Commits format, such as feat, fix, or docs. Git is a tool for tracking changes to code.
dev
Developer tools — debug, commit, PR, code review, refactoring.
fix
Quick bugfix commit. Use for fix bug, bugfix, patch, hotfix, correct error.
Checkpoint Commit
Commit changes at meaningful checkpoints throughout the workflow.