All apps

First-party app · Code Review

code-review

Deep-review a GitHub pull request one file at a time, riskiest changes first. It works through the GitHub CLI you are already signed in to. Findings stay in a local log on your machine — nothing is ever posted back to the PR.

Before you install

A first-party app of PersonalClaw v0.3.9

No scan on record before install

PersonalClaw publishes no scan of its own apps before you install one.

PersonalClaw runs its own scan of the actual code of every app it installs: this one is rescanned when you install, and that scan is what can stop an install.

Its row on Compare: install rescan

Compatibility
Works with PersonalClaw v0.3.9

What it gets

Permissions
  • storage: true
  • network: true
Its own network permission
On. Its own network permission is a declaration, not a fence.

What it starts

The programs on this machine it starts, as install consent names them.

  • gh: Code Review reads each pull request's diff from GitHub with gh pr diff, and personalclaw doctor runs gh auth status. It never writes to GitHub.

    It runs with your own gh sign-in and settings.

What it reaches

Hosts it names
Not declared in this release's manifest

Its own code has no host list at this release: any hosts it names are for the programs, servers and sources it starts or fetches, not everything it can reach. Its own network permission is a declaration, not a fence.

Secrets you would enter

Settings marked secret
Not declared in this release's manifest

What installing it gives and runs

The manifest's own declarations, under the names install consent shows them by and in its order. The Store adds, at install, which of them run as you.

Permissions it is granted
{
  "storage": true,
  "network": true
}
Programs on this machine it starts
[
  {
    "program": "gh",
    "why": "Code Review reads each pull request's diff from GitHub with gh pr diff, and personalclaw doctor runs gh auth status. It never writes to GitHub.",
    "inherits": [
      "sign-in",
      "settings"
    ]
  }
]
Provider modules the gateway loads
[
  {
    "type": "tool",
    "implementation": "provider:create_provider"
  }
]
What it runs for personalclaw setup
"app_cli:setup"
What it runs for personalclaw doctor
"app_cli:doctor"

Not declared in this release's manifest:

  • Scheduled jobs
  • Python packages installed for it
  • Engine packages it can install
  • What it needs that PersonalClaw does not install
  • npm packages installed for it
  • Places outside its folder it writes
  • Pages it adds to the dashboard
  • Components it adds to the dashboard
  • A server process of its own
  • The sandbox tier its server runs in
  • Command run after install
  • Command run after an update
  • Command run when it is switched on
  • Command run when it is switched off
  • Command run before it is removed
  • Connector sources it parses
  • MCP servers it adds
  • Skills it installs

Where it comes from

Publisher
PersonalClaw
License
MIT
Pinned commit
169cbc4f8fc59cd42a65a6a3546235bc49ab3b22
Signer
Not declared in this release's manifest

From review to enable

  1. Held and scanned. An install stages the app in quarantine, checks its signature, and runs the shared supply-chain scanner over the staged bytes before anything is shown for consent. A registry's recorded verdict is not read at install: the scan that can stop it is this one.Its row on Compare: install rescan
  2. A dangerous verdict ends it. A dangerous verdict returns a refusal before consent is asked, so there is no consent to give and no switch that skips it. A warning verdict asks for your consent instead.Its row on Compare: dangerous verdict
  3. You review and consent. The review records a digest of the staged bytes, and an install committed against different bytes is refused: it needs consent again, because the app changed after it was reviewed. An update that changes what the app gets asks for consent again too.Its row on Compare: consent
  4. Its setup runs, then you switch it on. Nothing it declares runs before your consent; an app already installed is offered as an update instead.

To install it and switch it on

  1. In PersonalClaw, open the Store.
  2. Find code-review.
  3. Review what it gets and runs, and consent.
  4. Install it, then switch it on.

Evidence

code-review/app.json at the pinned commit, as written, with the blob hash git lists for it: ec1dfd6d6202e9ee2c362e47db5cfb2b6348ad2b

Open it at the commit

{
  "name": "code-review",
  "version": "0.1.5",
  "displayName": "Code Review",
  "description": "Deep-review a GitHub pull request one file at a time, riskiest changes first. It works through the GitHub CLI you are already signed in to. Findings stay in a local log on your machine — nothing is ever posted back to the PR.",
  "icon": "GitPullRequest",
  "author": "PersonalClaw",
  "license": "MIT",
  "minPersonalClawVersion": "0.2.3",
  "requiresCoreFeatures": [
    "closing-streams"
  ],
  "tags": [
    "tool",
    "code",
    "review",
    "github"
  ],
  "cli": {
    "setup": "app_cli:setup",
    "doctor": "app_cli:doctor"
  },
  "permissions": {
    "storage": true,
    "network": true
  },
  "launches": [
    {
      "program": "gh",
      "why": "Code Review reads each pull request's diff from GitHub with gh pr diff, and personalclaw doctor runs gh auth status. It never writes to GitHub.",
      "inherits": [
        "sign-in",
        "settings"
      ]
    }
  ],
  "provider": {
    "id": "tools",
    "label": "Review a pull request file by file",
    "type": "tool",
    "implementation": "provider:create_provider",
    "capabilities": [
      "code"
    ],
    "settingsSchema": {
      "type": "object",
      "properties": {
        "fanout": {
          "type": "string",
          "enum": [
            "model",
            "plan",
            "static"
          ],
          "default": "model",
          "x-meta": {
            "label": "Per-file fan-out",
            "help": "model — reviews each changed file with its own isolated model call. plan — skips the model and returns a per-file plan your agent can delegate to subagents. static — runs only the built-in diff checks, with no model."
          }
        },
        "concurrency": {
          "type": "integer",
          "default": 3,
          "minimum": 1,
          "maximum": 8,
          "x-meta": {
            "label": "Concurrent per-file reviews",
            "help": "How many files are reviewed at once in model fan-out.",
            "tags": [
              "advanced"
            ]
          }
        },
        "max_files": {
          "type": "integer",
          "default": 40,
          "minimum": 1,
          "maximum": 200,
          "x-meta": {
            "label": "Files per review",
            "help": "Cap the fan-out to the N heaviest files. The rest still appear in the weight table, named as skipped.",
            "tags": [
              "advanced"
            ]
          }
        },
        "model_entry": {
          "type": "string",
          "default": "",
          "x-meta": {
            "label": "Model entry",
            "help": "Which configured model runs the per-file reviews. Empty uses the first chat-capable provider from Settings → Models.",
            "tags": [
              "advanced"
            ]
          }
        },
        "timeout_secs": {
          "type": "integer",
          "default": 20,
          "x-meta": {
            "label": "GitHub CLI Timeout",
            "help": "Maximum seconds to wait for `gh pr diff` before giving up.",
            "tags": [
              "advanced"
            ]
          }
        }
      }
    }
  }
}
Scan verdict
No scan on record before install
Scan time
No scan is published before install
Blocking findings
No scan is published before install
Scanner version
No scan is published before install

PersonalClaw publishes no scan of its own apps before you install one.

  • Every app is scanned again when you install it, whatever its listing says.

    An install stages the app in quarantine, checks its signature, and runs the shared supply-chain scanner over the staged bytes before anything is shown for consent. A registry's recorded verdict is not read at install: the scan that can stop it is this one.

    apps/app_manager.py at v0.3.9
  • A dangerous scan verdict stops the install, and nothing overrides it.

    A dangerous verdict returns a refusal before consent is asked, so there is no consent to give and no switch that skips it. A warning verdict asks for your consent instead.

    apps/app_manager.py at v0.3.9
  • Consent covers exactly what you reviewed, and an app that changed asks again.

    The review records a digest of the staged bytes, and an install committed against different bytes is refused: it needs consent again, because the app changed after it was reviewed. An update that changes what the app gets asks for consent again too.

    apps/app_manager.py at v0.3.9
  • A setting an app marks secret is kept in the credential store and never shown back.

    The app's settings file holds only a reference, the value lives in the credential store, and every route that shows settings masks it. The app's own code receives the value when it runs.

    apps/secret_fields.py at v0.3.9

PersonalClaw/PersonalClawApps @ 169cbc4f8fc5 · code-review/app.json