BC opencode-acp-control
Control OpenCode directly via the Agent Client Protocol (ACP). Start sessions, send prompts, resume conversations, and manage OpenCode updates.
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
ProcedureGitHubAI and agentsInfrastructuretype and topics are labelled automatically from the skill text
The same skill appears in 1 more place: ClawHub
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 5
✓ No critical or high findings
Medium and low: 5
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:159High-entropy token-like string (may be an id, hash or a credential)ses_…VVy 2026-01-11 15:30 12
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:160High-entropy token-like string (may be an id, hash or a credential)ses_…BkS 2026-01-10 09:15 5
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:161High-entropy token-like string (may be an id, hash or a credential)ses_…23Q 2026-01-09 14:22 8
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:194High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded){"jsonrpc":"2.0","id":1,"method":"session/load","params":{"sessionId":"ses_…VVy","cwd":"/path/to/project","mcpServers":[]}}quoted -
low Dangerous commands
cmd-pipe-to-shellSKILL.md:284Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host; quoted — discussed, not commanded)- Suggest manual update: `curl -fsSL https://opencode.dev/install | bash`
vendor-hostquoted
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 51/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 5 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 85Steps. 33 steps, 1 vague phrases
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2370 tokens
- low 12 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +3Description length 143: enough signal without eating the budget
- +4Structure: 29 headings
- +3Step-by-step instructions: 33 items
- +4Has examples (19 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.
External checks
ClawHub: suspicious
The skill is mostly coherent for controlling OpenCode, but its update guidance includes broad process termination and an unsafe remote installer command that users should review carefully before installing.
LLM: suspicious (high) · VirusTotal: benign · 10 Sept 2026