SKILLEMALL.ai

BC opencode-acp-control

Use when an AI agent needs to start, drive, or monitor an OpenCode CLI session programmatically over the Agent Client Protocol (ACP). Triggers include requests to "spawn OpenCode", "control OpenCode from another agent", "automate OpenCode over JSON-RPC", "resume an OpenCode session", or any task that requires the agent to act as an ACP client rather than an interactive user. Provides the JSON-RPC 2.0 framing, session lifecycle, polling strategy, permission-request handling, and update detection needed to wrap OpenCode from inside another AI agent.

ClawHub Agent Skills author: Bastian Nicolas Berrios Alarcon v0.3.1 MIT-0 10 files body ≈ 1 912 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency

IntegrationAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
B
87/100
safety, quality, tests
Safety 60%
85
Quality 40%
89
Run on models
none yet
Process rating
C
54/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 3

    ✓ No critical or high findings

    Medium and low: 3
    • medium Dangerous commands cmd-pipe-to-shell CHANGELOG.md:56
      Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)
      - Added safety note alongside the `curl | bash` install command.
      quoted
    • medium Dangerous commands cmd-pipe-to-shell SKILL.md:213
      Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)
      install (review the installer script before piping `curl | bash`):
      quoted
    • medium Dangerous commands cmd-pipe-to-shell SKILL.md:216
      Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)
      curl -fsSL https://opencode.ai/install | bash
      vendor-host

    Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 54/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 30Running it twice. 7 mutating operations with no state check
    • 40Consistency. Frontmatter name (opencode-acp-control) differs from the folder (opencode-acp-control-3)
    • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 85Steps. 37 steps, 1 vague phrases
    • 100Failures and branches. 1 branches, has a failure section
    • 100Execution cost. Instruction body is 1912 tokens
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low 11 top-level sections: this looks like several domains in one skill

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 4 example trigger phrases
    • +3Description length 553: enough signal without eating the budget
    • +4Structure: 19 headings
    • +3Step-by-step instructions: 37 items
    • +4Has examples (10 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.

    External checks

    ClawHub: suspicious
    The skill mostly matches its OpenCode automation purpose, but it includes under-scoped update/process-control instructions and a demo that auto-approves privileged tool requests.
    LLM: suspicious (high) · 7 Aug 2026