Metal Mantra / AGENT INTELLIGENCEPublic evidence reportAUTOMATED SIGNAL. NOT CERTIFICATION.
PUBLIC REPORT · ADDED BY METAL MANTRA / AGENT SIGNAL v0.2

opcode.

Scanned repository says: opcode is a powerful desktop application that transforms how you interact with Claude Code. Built with Tauri 2, it provides a beautiful GUI for managing your Claude Code sessions, creating custom agents, tracking usage, and much more.

Metal Mantra scanned this public repository on its own initiative; the maintainer did not submit it. Maintainers: scan the repository yourself to take this report over, or contact us.

Inspect GitHub source

22.4k starsAGPL-3.0pushed 23d ago

0community interest

Votes show community interest, not safety. They never change this score.

AUTOMATED SIGNAL78/100BBBNot security certification
START HERE

Review findings need attention.

Domain ownership not verified

Inspect the findings
WHAT THIS DOES NOT ESTABLISH

Runtime safety, real-world agent capability, fitness for your use case or independent certification.

Scan scope121 / 121Complete eligible-file selection · not the entire repository
Recorded findings9Heuristic matches requiring human review
SnapshotOct 12, 2026UTC · engine 0.4.0
DNS at scan timeUnverifiedDomain control is not security certification
01 / KNOW THE REPOSITORY

What the source
actually tells us.

Structured, cited information from the scanned archive. Repository-authored claims are labeled and never treated as verified capabilities.

INSPECTED SOURCE121 / 121Complete eligible selection
READMEReadRepository-authored information
MANIFESTS1package.json

Who it is for

  • Stated purpose · repository says · unreviewed

    opcode is a powerful desktop application that transforms how you interact with Claude Code. Built with Tauri 2, it provides a beautiful GUI for managing your Claude Code sessions, creating custom agents, tracking usage, and much more.

    README.md:37
  • Stated purpose · repository says · unreviewed

    Think of opcode as your command center for Claude Code - bridging the gap between the command-line tool and a visual experience that makes AI-assisted development more intuitive and productive.

    README.md:39

What it can do

No explicit capability or integration was extracted; that does not mean none exists.

What adoption takes

  • Stated deployment · repository says · unreviewed

    Launch opcode: Open the application after installation

    README.md:111
  • Stated prerequisite · repository says · unreviewed

    Claude Code CLI: Install from Claude's official site

    README.md:160
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on zod.

    package.json:62
  • Stated deployment · repository says · unreviewed

    Welcome Screen: Choose between CC Agents or Projects

    README.md:112
  • Stated prerequisite · repository says · unreviewed

    Before building opcode from source, ensure you have the following installed:

    README.md:168
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on @hookform/resolvers.

    package.json:22
  • Stated deployment · repository says · unreviewed

    First Time Setup: opcode will automatically detect your ~/.claude directory

    README.md:113
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on @radix-ui/react-dialog.

    package.json:23
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on @radix-ui/react-dropdown-menu.

    package.json:24
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on @radix-ui/react-label.

    package.json:25
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on @radix-ui/react-popover.

    package.json:26

Limits and terms

  • Stated limitation · repository says · unreviewed

    opcode prioritizes your privacy and security:

    README.md:379
  • Declared license · manifest declares · unreviewed

    Manifest declares AGPL-3.0 as its license.

    package.json:5
  • Stated limitation · repository says · unreviewed

    Process Isolation: Agents run in separate processes

    README.md:381
  • Stated limitation · repository says · unreviewed

    Permission Control: Configure file and network access per agent

    README.md:382

Observed technical context

TypeScript · 121 selected filesTool-calling reference · static only

These are references in selected source files, not proof that a feature works at runtime.

Read from commit d1ca30a at Oct 12, 2026, 5:24 AM UTC. Source links open that exact commit. Repository statements are unreviewed and do not affect the score.

02 / FINDINGS FIRST

What needs
a closer look.

Critical details are withheld publicly for the first 30 days after a scan. A matched pattern is a lead for investigation, not a confirmed vulnerability.

Dependencies: 424 exact runtime versions from package-lock.json checked against OSV.dev on Oct 12, 2026; 13 with known advisories. Reachability is not checked.

9 findings
MAJOR

Domain ownership not verified

TRUST001 · Entity trust

Metal Mantra could not confirm that the owner controls the stated domain. The domain may belong to someone else.

SUGGESTED ACTION

Verify the domain using the Metal Mantra DNS TXT challenge.

opcode.sh · location unavailable
MAJOR

Dependency with a high-severity advisory

DEP001 · Security & privacy

tar 7.4.3 (npm) has known advisories: GHSA-23hp-3jrh-7fpw, GHSA-34x7-hfp2-rc4v, GHSA-83g3-92jg-28cx, GHSA-8qq5-rm4j-mr97, GHSA-8x88-c5mf-7j5w (highest severity critical). node-tar: Decompression/parse DoS via unlimited input

SUGGESTED ACTION

Upgrade to a fixed version listed in the advisory and regenerate the lockfile.

package-lock.json:7389
MAJOR

Dependency with a high-severity advisory

DEP001 · Security & privacy

braces 3.0.3 (npm) has a known advisory: GHSA-vfj7-8cjw-p6xm (highest severity high). braces vulnerable to stack-exhaustion denial of service through deeply nested patterns

SUGGESTED ACTION

Upgrade to a fixed version listed in the advisory and regenerate the lockfile.

package-lock.json:3858
MAJOR

Dependency with a high-severity advisory

DEP001 · Security & privacy

lodash 4.17.21 (npm) has known advisories: GHSA-f23m-r3pf-42rh, GHSA-r5fr-rjxr-66jc, GHSA-xxjr-mmjv-4gpg (highest severity high). lodash vulnerable to Code Injection via `_.template` imports key names

SUGGESTED ACTION

Upgrade to a fixed version listed in the advisory and regenerate the lockfile.

package-lock.json:5337
MINOR

Privacy Policy link not confirmed

TRUST003 · Entity trust

No privacy policy link was found on the stated homepage. Buyers cannot see how the vendor handles their data.

SUGGESTED ACTION

Expose a clear Privacy Policy link on the official homepage.

opcode.sh · location unavailable
MINOR

Terms link not confirmed

TRUST004 · Entity trust

No terms link was found on the stated homepage. Buyers cannot see the conditions that apply to using the service.

SUGGESTED ACTION

Expose a clear Terms link on the official homepage.

opcode.sh · location unavailable
MINOR

Dependency with a known advisory

DEP002 · Security & privacy

mdast-util-to-hast 13.2.0 (npm) has a known advisory: GHSA-4fh9-h7wg-q85m (highest severity moderate). mdast-util-to-hast has unsanitized class attribute

SUGGESTED ACTION

Upgrade to a fixed version listed in the advisory and regenerate the lockfile.

package-lock.json:5632
MINOR

Dependency with a known advisory

DEP002 · Security & privacy

prismjs 1.27.0 (npm) has a known advisory: GHSA-x7hr-w5r2-h6wg (highest severity moderate). PrismJS DOM Clobbering vulnerability

SUGGESTED ACTION

Upgrade to a fixed version listed in the advisory and regenerate the lockfile.

package-lock.json:6858
MINOR

Dependency with a known advisory

DEP002 · Security & privacy

diff 8.0.2 (npm) has a known advisory: GHSA-73rr-hh4g-fpgx (highest severity low). jsdiff has a Denial of Service vulnerability in parsePatch and applyPatch

SUGGESTED ACTION

Upgrade to a fixed version listed in the advisory and regenerate the lockfile.

package-lock.json:4304
03 / EVIDENCE & LIMITS

The boundary
is part of the result.

What was scanned
121 of 121 eligible files · Complete selection.
Supported static source patterns and domain checks; no runtime execution.
What remains unknown
Unscanned files, external dependencies, production configuration, actual agent behavior and evidence beyond the configured checks.
Source location
Links open the current repository HEAD. Source may have changed since this snapshot.
Something looks wrong?
Tell us if a finding, scope or claim on this report needs a correction. Report a problem with this report
Entity trust · 15% of v0.2
Includes DNS ownership, HTTPS and policy evidence. Verification is domain control, not a security certificate.
DNS: unverifiedHTTPS: availablePrivacy: not confirmedTerms: not confirmed
04 / THE METHOD BEHIND THE NUMBER

Open the
calculation.

Each pillar starts at 100. Rule deductions reduce its score; weights determine the overall contribution.

01

Security & privacy

6 findings · 25% weight
58/10014.5 pts
02

Guardrails & loop control

0 findings · 25% weight
100/10025.0 pts
03

Schema & tooling

0 findings · 20% weight
100/10020.0 pts
04

Token & cost efficiency

0 findings · 15% weight
100/10015.0 pts
05

Entity trust

3 findings · 15% weight
25/1003.8 pts
Inspect the current standard
USER REPORTS

Did opcode work for people?

No user reports yet.

Each report is one signed-in GitHub account saying what happened. We do not verify that the account ran the agent, and reports never change the automated score or grade. For a security problem, use the disclosure page instead of a public note.

Sign in with GitHub to add a report

SHARE THE EVIDENCE

A signal.
Not a seal.

Share the full report so its scope and limits travel with the score.

Metal Mantra automated signal 78/100, not certified