Grades are a hygiene check, not a security guarantee.

Claude Code, Skill

Agent Alchemy

A plugin suite and developer toolkit that extends Claude Code into a structured development platform — from specs to tasks to autonomous execution.

Compatibility: Not stated.

Grade C

One Medium finding. Read the findings before installing.

Graded by PlugVetRubric v2

Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.

SECRETS_PATH_CREDENTIAL

Why this grade

  • SECRETS_PATH_CREDENTIAL Medium

    Mentions a credential store path (~/.ssh, id_rsa, .npmrc, .aws/credentials, credentials.json, .netrc).

    agent-tools/src/agent_tools/sources/git.py, line 261 "For SSH: ssh-add ~/.ssh/id_ed25519 or check ~/.ssh/config. "

Any High, or two or more Medium findings, give D. One Medium gives C. Low findings or a security Note give B. Each code names a finding behind the letter.

Grades are a hygiene check of the source at the commit shown, on the date checked, not a security audit or a guarantee. The free directory grades are automated. Before release, a PlugVet engineer reviews every paid report and any grade we hold back, including all F grades, against the source code and the evidence we quote.

What was checked

Plain notes from the hygiene checks.

  • Permissions

    Note

    requests shell access. The manifest names this permission.

    PERMISSION_SHELL_DECLARED

    agent-tools/src/agent_tools/sources/git.py, line 107

    result = subprocess.run(

  • Install and update

    Pass

    No install-time script found, and dependencies are pinned or absent.

  • Network

    Concern

    can reach a host that is not written as a fixed address.

    NETWORK_NO_FIXED_HOST

    agent-tools/src/agent_tools/sources/registry.py, line 257

    with urllib.request.urlopen(req, timeout=30) as resp:

    apps/task-manager/src/lib/api.ts, line 19

    const response = await fetch(`${API_BASE}/task-lists`)

    apps/task-manager/src/lib/api.ts, line 28

    const response = await fetch(`${API_BASE}/tasks/${encodeURIComponent(taskListId)}`)

    Show more

    apps/task-manager/src/lib/api.ts, line 39

    const response = await fetch(

    claude/core-tools/skills/language-patterns/SKILL.md, line 56

    const response = await fetch('/api/data');

    claude/core-tools/skills/language-patterns/SKILL.md, line 99

    const response = await fetch(`/api/users/${id}`);

    ported/20260304-102613/core-tools/skills/language-patterns/SKILL.md, line 55

    const response = await fetch('/api/data');

    ported/20260304-102613/core-tools/skills/language-patterns/SKILL.md, line 98

    const response = await fetch(`/api/users/${id}`);

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_PATH_CREDENTIAL SECRETS_PATH_DOTENV

    agent-tools/src/agent_tools/sources/git.py, line 261

    "For SSH: ssh-add ~/.ssh/id_ed25519 or check ~/.ssh/config. "

    claude/claude-tools/skills/claude-code-teams/references/orchestration-patterns.md, line 720

    rer found that JWT_SECRET is loaded from .env but you noted tokens are validated in m

    .gitignore, line 37

    # Environment files

    Show more

    .gitignore, line 39

    !.env.example

    agent-tools/README.md, line 357

    - **SSH**: Ensure your SSH key is loaded (`ssh-add ~/.ssh/id_ed25519`) and the remote host is in `~/.ssh/config`.

    claude/plugin-tools/references/mcp-converter.md, line 52

    | `mcpServers.<name>.env` | object | No | Environment variables to set for the server process. Values may contain `${CLAUDE_PLUGIN_ROOT}` for path resolution. |

  • Agent instructions

    Pass

    No instruction to ignore earlier instructions or to hide a step.

  • Obfuscation

    Note

    the file cap was reached before every file was read.

    OBFUSCATION_FILE_CAP_REACHED

    ported/20260305-085418/core-tools/skills/technical-diagrams/references/er-diagrams.md, line 1

    # ER Diagrams Reference

  • Licence

    Pass

    A licence file is present (LICENSE).

  • Maintainer activity

    Pass

    The latest commit is within the last 365 days.

Note

Hygiene check of commit fc1a336b8267. requests shell access. The manifest names this permission. can reach a host that is not written as a fixed address. reads a credential or environment file. the file cap was reached before every file was read.

Date and source

Date checked:

View source

github.com

Commit graded: fc1a336b8267e70579af8517d14718e626824e54

This link goes to the original host. PlugVet does not host or check what you download from there, and installing it is your own decision and risk.

Read how this letter is chosen