Power your agent
คำสั่งของผู้เผยแพร่เอง ไม่ใช่เอนด์พอยต์ของ PlugMCP
Host a copy with our keys and logs.
npx -y @mirnoorata/[email protected]Claude Code ไม่มีลิงก์ติดตั้งสำหรับคำสั่งแบบโลคัล ให้คัดลอกคำสั่งด้านล่างแล้วรันในเทอร์มินัล
CODEXA_MCP_STRUCTURED_BUDGET_BYTES=<value> claude mcp add io.github.mirnoorata-codexa -- npx -y @mirnoorata/codexa@0.20.1รันในเทอร์มินัล
{ "mcpServers": { "io.github.mirnoorata-codexa": { "command": "npx", "args": [ "-y", "@mirnoorata/[email protected]" ], "env": { "CODEXA_MCP_STRUCTURED_BUDGET_BYTES": "<value>" } } }}claude_desktop_config.json
URL แบบรีโมตหรือคำสั่งบนเครื่องของคุณ? การติดตั้งสองแบบต่างกันอย่างไร
รันบน PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
เปิดจากผู้เผยแพร่
Understand the code. See what a change could affect. Check the evidence.
Codexa helps developers and AI coding assistants work on a repository with more context and fewer guesses. It builds a local map of your code, connects files to their dependencies and tests, and produces readable reports about proposed and completed changes.
Codex-native codebase intelligence context compiler and query-only MCP server.
Think of it as a map and a change checklist for your project. The person—or coding assistant—still drives. Codexa points out the bridge you might want to check before taking the truck across it.
Use it from a terminal, with Codex, Claude Code, or another compatible coding assistant, or in GitHub Actions to help review pull requests. The core needs no API key, hosted account, or database. Codexa is free and MIT-licensed; your AI assistant and any optional hosted services have their own requirements and costs.
Get started · Connect an assistant · Everyday use · GitHub reviews · Troubleshooting · Full reference
Maintainer expectations: Codexa is a focused project maintained by one person in spare time. Expect replies in days to weeks. Please discuss larger changes before opening a PR; see Contributing.
For example, changing a login timeout can affect more than one number. Codexa can help locate the setting, identify code that uses it, suggest related tests, and flag edits outside the agreed scope. Its findings depend on what it can read and connect in your repository; it cannot predict every runtime behavior.
Codexa supplies context and checks. Your editor or assistant makes the edits, and your project's tests establish whether the behavior works. A green-looking report is useful evidence, not a force field.
You need Node.js 22 or newer, npm (included with Node.js), Git, and a local Git repository—the project folder you want to inspect. You do not need to clone Codexa itself or install an AI assistant to use the terminal commands.
Run these commands in a terminal:
node --version
git --version
npm install -g @mirnoorata/codexa
codexa --version
Replace /path/to/project with your repository's actual folder path. Quote the
path if it contains spaces. In the examples below, . means “this folder.”
cd /path/to/project
codexa index .
codexa repo-map .
index reads the repository and creates the local map. repo-map shows the
ranked files and modules. This terminal-only path needs no assistant setup.
Ask a question relevant to your project:
codexa search . --query "login timeout"
This is an example query, not a built-in demo: results depend on your code. For ongoing use, follow the generated-files guidance and choose your assistant setup below.
No global install? Prefix commands with npx -y @mirnoorata/codexa, for
example npx -y @mirnoorata/codexa index /path/to/project. npm may download the
package; the default indexing itself runs locally.
Codexa uses MCP (Model Context Protocol), the connection that lets an AI assistant ask external tools for information. The assistant runs the model; Codexa provides repository context. Install and sign in to your chosen assistant separately.
From your project folder:
codexa init . --agents-md
codexa session-start .
This creates the index, adds the Codexa server to .codex/config.toml, installs
Codex startup/edit hooks, and adds a small managed workflow block to AGENTS.md.
Omit --agents-md if you want to manage your own agent instructions. If a
Codexa plugin already supplies your MCP connection, avoid registering a second
server for the same repository.
Open or reload that same project in Codex and trust it when prompted.
Project-scoped MCP configuration is loaded only for trusted projects. In
Codex CLI, /mcp shows active connections; see the
official MCP setup guide.
A successful session-start check confirms observable setup and index state;
it cannot prove that an already-running assistant has loaded the server.
Windows: use codexa init . --agents-md --no-hooks for native Windows
MCP-only setup. The generated shell hooks require a POSIX environment such as
WSL. macOS and Linux can use the standard command above.
For the simplest connection:
codexa init . --claude --claude-md --no-hooks
codexa session-start .
This also writes the server entry to .mcp.json and workflow guidance to
CLAUDE.md. Restart Claude Code in that repository and approve the project MCP
server if prompted. --no-hooks disables Codexa's Codex hooks; this setup gives
Claude tools and instructions, without Claude hooks or slash commands.
Want automatic startup guidance, a review hook, and commands such as
/codexa-plan and /codexa-review? Use the bundled
Claude Code plugin. Choose either
the plugin or the .mcp.json connection above to avoid duplicate servers.
Configure a local command server in your client's MCP settings:
{
"mcpServers": {
"codexa": {
"command": "codexa",
"args": ["serve", "/path/to/project", "--auto-refresh"]
}
}
}
Replace the path and adapt the outer configuration format to your client.
The client must be able to find codexa and access the repository. It launches
the server; serve is not an interactive chat command.
Fresh installs expose three tools: search, change_plan, and capabilities.
That small menu is intentional: capabilities provides access to the remaining
operations. Use --tools full with init or serve if your client needs every
operation listed directly.
The default connection uses a local process. Optional HTTP transport binds only to the local machine; Codexa does not ship a public remote server.
Use Codexa when it resolves uncertainty. A small fix in a known file may need only direct inspection and the project's normal tests. No ceremony is required for changing a comma. A change spanning several files benefits more from planning and review.
For a coding assistant, a useful request is:
Find where login timeouts are handled. Use Codexa if the target or impact is unclear. Before a substantial edit, save a change plan. Make the change, run the relevant checks, and review the result against the plan. Tell me what remains unverified.
You can also run that workflow yourself. This example assumes your repository
has src/auth.ts; substitute a real file and task:
codexa change-plan . --task "Adjust the login timeout" --file src/auth.ts --task-id login-timeout --save-snapshot
Read the plan, make the edits, and run the checks appropriate to your project. Then review the work before committing, while the edits are still visible as local changes:
codexa post-edit-review . --task-id login-timeout
Report checks you actually ran with --ran-command. For example, only if
npm test is a real check in your project and you ran it:
codexa post-edit-review . --task-id login-timeout --ran-command "npm test"
That flag records a claim; it does not execute the command. Codexa checks
whether the reported command could cover the relevant work. A command that
hides failures, such as npm test || true, does not earn credit. Codexa cannot
detect a completely fabricated report.
For a formal handoff, codexa prove . --task-id login-timeout summarizes the
saved plan, available evidence, and unresolved gaps. Supply actual command
reports or selected verification artifacts when the handoff needs them.
Startup and edit hooks reduce manual steps, but their reviews do not replace one final review with the actual test evidence. Detailed workflow, invariants, and repeat-attempt controls are in the reference.
Run these from the project root, using your own file names and questions:
Most context commands refresh an outdated index automatically. Use
codexa --help, codexa <command> --help, or the
command reference for more options.
Codexa can generate a report for a committed branch without an AI assistant.
From a clean checkout of that branch, with origin/main available locally:
git fetch origin
codexa review . --base origin/main --head HEAD
codexa review . --base origin/main --head HEAD --format json
Replace origin/main if your repository uses a different base branch. Codexa
compares changes since the branches' common ancestor. HEAD must match the
checked-out commit, and the index must represent that clean checkout.
To add the same review to GitHub Actions:
codexa init . --ci
Review and commit the generated .github/workflows/codexa-review.yml with your
normal PR process. It checks out the PR's exact head, uses read-only repository
permissions, and writes results to the Actions summary and annotations. It
does not post PR comments or run your project's tests. Keep your existing CI.
The default observe mode reports findings without blocking on them. warn
adds warning annotations. Explicit fail mode can block on local plan drift,
an unavailable requested local plan, or reported command failures. Suggested
but unrun tests alone do not fail the review. Invalid inputs and setup errors
can fail in any mode.
See committed change receipts for plan comparison, trust limits, and CI options.
Add these generated paths to your project's .gitignore (Codexa does not add
them for you):
.codex/codebase/
.codex/cache/
.codex/static-analysis/
If your MCP config and hooks are local to your machine, ignore those files too.
Avoid ignoring the entire .codex/ directory if your team tracks policies or
setup scripts there. Inspect generated launch paths before committing wiring;
init supports portable wiring for already-tracked files. Each teammate and
fresh checkout still needs its own install and index.
Re-running init refreshes Codexa's managed configuration and preserves other
MCP server entries. Optional instruction blocks replace only the region between
Codexa's markers. --policy-pack creates local proof policies without
replacing existing policy files. See the
setup reference
for portability and managed-file behavior.
There is no web dashboard or hosted indexing service to operate. Optional embeddings, TypeSafe, language-server assistance, scanner imports, session memory, and AutoVerify are documented in the reference.
Update with npm install -g @mirnoorata/codexa@latest, re-run your chosen init
command in each repository, and reload the assistant connection. Reuse optional
flags such as --claude or --agents-md to refresh those integrations. Plain
init preserves the existing tool profile; use --tools core to switch it.
To remove Codexa, first disable its server/plugin and remove only its managed
config entries, hooks, and instruction blocks. Preserve other tools' settings.
Then run npm uninstall -g @mirnoorata/codexa. Generated indexes can be removed;
export any plans or evidence you want to keep before deleting .codex/cache/.
Remove its CI workflow too if you enabled one. There is no all-in-one uninstall
command.
A Git worktree is another checkout of the same repository. Run codexa init
inside each one so its configuration and index match its own code. Automate
that step in your project's setup if you create worktrees frequently.
When developing Codexa itself, this repository includes a Codex local environment and bootstrap scripts that install locked dependencies, build the package, and verify worktree setup. Those scripts are for this repository; ordinary users do not need to copy them. See the worktree and recovery guide.
Codexa's engine is TypeScript. Its main path is:
Repository → local index → relevant context and change analysis → evidence report
To build from source:
git clone https://github.com/mirnoorata/codexa.git
cd codexa
npm ci
npm run build
npm link
npm run check
npm link makes this checkout's codexa command available locally; skip it if
you prefer node dist/cli.js. The full gate builds and type-checks the package,
checks hygiene and public paths, runs tests, and checks the startup context
budget. See Contributing and the
architecture reference.
The repository includes reproducible retrieval evaluations and an agent A/B harness. These measure different things: finding useful context does not by itself prove that an assistant finishes tasks faster or better. An archived small agent pilot showed extra overhead without a completion benefit; it is not evidence of universal savings. Results, dates, caveats, and reproduction commands are kept in Public Proof.
GitHub Releases are the visible source timeline for the current project.
Maintainers normally use Release Automation. An explicitly
requested manual npm run release:github generates a changelog-style summary,
changed-area summary, restore instructions, and forward-only PR rollback commands.
See the manual release reference.
Release Please prepares version/changelog PRs and GitHub Releases using the
repository's GITHUB_TOKEN. This does not publish npm on every main merge:
ordinary changes land first, and npm publishing follows a published release.
See release automation and the
public release checklist.
The maintainer workflow publishes through GitHub Actions and npm trusted
publishing. It runs after an explicit Release Please dispatch or a manually
published GitHub Release (release: published), not a tag push alone.
After its release and security checks, the workflow runs:
npm publish --registry https://registry.npmjs.org --access public --tag latest --provenance --ignore-scripts
Package users only need the installation instructions above. Maintainers can find authentication and recovery procedures in the publishing reference.
Use Discussions for questions and Issues for reproducible bugs. Report vulnerabilities through private security advisories; see SECURITY.md.
Codexa is licensed under MIT.
Codex-native codebase intelligence context compiler and query-only MCP server.
{ "mcpServers": { "io.github.mirnoorata-codexa": { "command": "npx", "args": [ "-y", "@mirnoorata/[email protected]" ], "env": { "CODEXA_MCP_STRUCTURED_BUDGET_BYTES": "<value>" } } }}เครื่องมือ
ยังไม่มีรายการเครื่องมือ เซิร์ฟเวอร์แบบรีโมตจะได้รายการหลังการตรวจสอบสถานะครั้งแรก
FAQ
คัดลอกคอนฟิก stdio สำหรับ Cursor, Claude Desktop, Claude Code หรือ VS Code ได้ในหน้านี้ คอนฟิกนี้ใช้การติดตั้งของผู้เผยแพร่ ไม่ใช่พร็อกซีของ PlugMCP
ผู้เผยแพร่ระบุตัวแปรสภาพแวดล้อมเหล่านี้: CODEXA_MCP_STRUCTURED_BUDGET_BYTES
Codexa ทำงานแบบโลคัลผ่าน stdio
ตรวจสอบล่าสุดเมื่อ 2026-11-09 Codex-native codebase intelligence context compiler and query-only MCP server.