Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者提供的说明(英文原文)
Read and write checked code rationale stored outside source comments.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"koment": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/koment-dev/koment:3.2.0",
"mcp",
"--write"
]
}
}
}在终端中运行这条命令
claude mcp add koment -- docker run -i --rm ghcr.io/koment-dev/koment:3.2.0 mcp --write粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"koment": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/koment-dev/koment:3.2.0",
"mcp",
"--write"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"koment": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/koment-dev/koment:3.2.0",
"mcp",
"--write"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日
注册名称已通过 GitHub 账户 koment-dev 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(3.2.0)于2个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Docker。
同一分类中有:Spec Driven Development, Remote Desktop Commander, FactLot
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Cited CRE facts and deterministic calculators for agents: rent, CAM, debt sizing, IRR, parcel IDs.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Keep the _why_ next to your code — checked, so it can't quietly rot.
Someone wrote retry 5 times instead of 3, and there was a good reason. Six months later nobody remembers it, so it gets "simplified" back to 3 and the bug returns.
A comment was supposed to prevent that. Comments rot: they sit next to the code without being attached to it, and when the code changes nothing tells you the comment just became a lie. Your AI agent then reads that lie and acts on it.
You record the reason outside the source, anchored to the exact lines it explains. Then koment watches those lines. Change them, and it says so:
$ koment check
internal/auth/token.go drifted gotcha internal/auth/token.go 01KZN63VC5SZASDYJBMPDC03WB Without it, clients whose clock runs fast get logged out mid-request. Bit us in #412. 1 annotation across 1 file: 1 drifted koment: 1 annotation no longer resolves; revisit it or update the anchor
Exit code 1. The build stops. Nobody silently inherits a reason that no longer describes the code.
The records are YAML in .koment/, in your git repository. No database, no service, no account. They review in the same pull request as the change that motivated them.
[See it running →](https://why.koment.dev/) — koment's own annotations, published by a workflow you can copy.
This is where it earns its keep. Agents write explanatory comments constantly, and they edit code without reading why it was written that way. koment makes both of those fail *immediately*, while the agent is still working:
One MCP server serves Claude Code, Cursor, Codex, opencode, Hermes, Zed and the rest, so every agent reads the same reasoning through the same interface. Set yours up →
Humans get the same loop in the editor: a squiggle under the comment, and a quick fix offering *convert to annotation* or *keep it, on the record*.
brew install koment-dev/tap/koment
Other ways
mise use -g github:koment-dev/koment # mise
go install github.com/koment-dev/koment/cmd/koment@latest docker run --rm -v "$PWD:/repo" -w /repo ghcr.io/koment-dev/koment:3 check
In GitHub Actions, uses: koment-dev/koment@v3. Or take a checksum-listed binary for Linux, macOS or Windows on amd64/arm64 from the latest release — every other channel is built from those same artifacts.
From inside any git repository:
koment bootstrap
That sets up .koment/ and wires whichever agents you use. Now record a reason and watch it get checked:
koment add src/auth.go \
--excerpt 'if token.Expiry.Before(now.Add(-clockSkew)) {' \ --kind gotcha \ --title 'Skew subtraction keeps fast clocks logged in' \ --body 'Without it, clients whose clock runs fast get logged out mid-request. Bit us in #412.'
koment check # ok
Now edit that line and run `koment check` again. It fails, and tells you which reasoning no longer matches its code. That is the entire product; the rest is delivering it to the people and agents who need it.
koment ui # read them in a browser
koment show src/auth.go
.koment/annotations/ .yaml, one file per annotation. Concurrent agents create independent files instead of replacing one shared list.| meaning | build | |
|---|---|---|
ok | found where it was last seen | passes |
ambiguous | several contextual candidates remain | fails |
drifted | file exists, the annotated code is gone | fails |
orphaned | the file is gone | fails |
koment check exits non-zero on ambiguous, drifted or orphaned. That is the whole mechanism: uncertain rationale is worse than no annotation, so it has to be impossible to ignore.koment reanchor --excerpt ' ' repoints it — keeping its id and creation date, recapturing context and the line for you. Nothing re-attaches automatically; a person confirms the reasoning still holds.Anchoring is by excerpt, never by line number — line numbers rot on the next edit above them. The commit hash *is* recorded, but only to reconstruct history; it never decides whether an annotation still applies. Those are two different questions with two different mechanisms.
Local writes change the checkout you are already reviewing. Served writes never touch a replica or push a default branch: they create an exact annotation on a deterministic branch and return only after its pull request exists. Static publications remain immutable and read-only.
Pick one. Each is a place to stop, not a step you have to take, and moving between them is not a migration — all three read the same .koment/ in git, so there is nothing to export, import or back up.
| you run | you get | |
|---|---|---|
| local | the CLI, koment ui --write, and koment mcp --write | humans and agents read and write the same checked records. Nothing to host. |
| published | one workflow file → GitHub Pages | everyone reads the annotations in a browser. No server, no auth to design, no cost. |
| served | the container or the Helm chart | authenticated, commit-stamped GitHub snapshots for several repositories, cross-repository search, reviewed annotation PRs, metrics |
One deployment serves many. Identity is assigned independently of provider path, and every refresh resolves a branch to one immutable commit before replacing a repository's active snapshot:
# yaml-language-server: $schema=https://raw.githubusercontent.com/koment-dev/koment/main/schema/server.schema.json
repositories:
The service starts only when a non-loopback listener has either trusted-proxy identity or scoped bearer credentials. Private repositories and reviewed writes also require a GitHub token. The Helm chart documentation shows the secret formats and boundary.
Local commands need none of this configuration — koment finds the owning checkout by walking up from the working directory.
koment publishes an OCI Helm chart to oci://ghcr.io/koment-dev/charts/koment:
helm install koment oci://ghcr.io/koment-dev/charts/koment \
--set repositories[0].remote=you/your-repo \ --set metrics.enabled=true \ --set metrics.serviceMonitor.enabled=true \ --set metrics.dashboard.enabled=true
The application port authenticates source, rationale, UI and MCP; only liveness and readiness are public. Metrics use a separate listener so an ingress cannot accidentally expose them with application authentication. The chart includes a Grafana dashboard, ServiceMonitor, hardened pod defaults, optional NetworkPolicy and disruption controls, and a digest-pinned helm test probe.
Every flag can be set from the environment. --flag-name becomes KOMENT_FLAG_NAME, and an explicit flag always wins.
KOMENT_CONFIG | strict served repository YAML |
KOMENT_CREDENTIALS_FILE | secret file of SHA-256 bearer hashes and repository scopes |
KOMENT_GITHUB_TOKEN_FILE | provider token file for private reads and reviewed writes |
KOMENT_LISTEN | local UI or unified service address |
KOMENT_HUMAN_WRITES | allow identities from the trusted OIDC proxy to create reviewed annotations |
KOMENT_TRUSTED_PROXIES | CIDRs allowed to assert forwarded human identity |
KOMENT_SYNC_INTERVAL | provider snapshot refresh interval |
KOMENT_METRICS | separate metrics listener; off unless set |
KOMENT_WRITE | enable local UI or stdio MCP mutations |
KOMENT_OUT | static publication output directory |
Git is the only authoritative record. Local reads resolve the YAML directly against the working tree; disposable read models cannot restore or overwrite Git.
koment --help lists every flag alongside its variable.
The reference VS Code extension starts koment lsp, renders annotation bodies as virtual inline text, reports drift and prohibited comments as diagnostics, and adds native add, reanchor, convert and explicit acknowledgement actions. The prose is never inserted into the source buffer. Every release attaches a signed VSIX and publishes the same artifact to the VS Code Marketplace and Open VSX.
Other editors can use the standard hover, diagnostics, code-lens, code-action and execute-command surface from koment lsp without reimplementing storage or anchoring.
Claude Code can install the repository's own project-scoped marketplace plugin:
/plugin marketplace add koment-dev/koment
/plugin install koment@koment-dev
It bundles writable MCP configuration, injects the strict procedure at session start and runs the policy gate before Claude can finish a turn. Install a released koment binary and run koment agents install in the repository first.
OpenCode ships a parallel plugin at integrations/agent-plugins/opencode/. Add @koment/opencode-koment to the plugin array in opencode.json; OpenCode installs it at startup. It requires the released koment binary on PATH, denies ordinary explanatory comment intent and runs the policy gate on session end. ADR 0144 records the package and generated-adapter boundary.
Codex ships the same policy surface as a local marketplace at integrations/agent-plugins/codex/. Install that checkout path with codex plugin marketplace add, then run codex plugin add koment@koment-dev. The release workflow also produces a signed archive. The plugin provides writable MCP tools, a standing skill and trusted lifecycle hooks. ADR 0151 records the package boundary.
koment agents install
koment mcp --write
The generated repository adapters give agents a strict procedure and configure the writable stdio server. It has
只显示了开头部分;其余内容请在仓库中阅读