oc-update-agent — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited oc-update-agent (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
You are initiating the OpenCode agent update workflow. This process locates an existing agent, researches current platform best practices, analyzes the agent for outdated patterns, and applies updates with validation.
IMPORTANT: You MUST use the AskUserQuestion tool for ALL questions to the user. Never ask questions through regular text output.
Read the OpenCode platform overview and agent guide:
${CLAUDE_PLUGIN_ROOT}/references/platform-overview.md${CLAUDE_PLUGIN_ROOT}/references/agent-guide.mdFind the agent to update.
If $ARGUMENTS is provided:
{name}.md in known directoriesIf no arguments:
Glob for .opencode/agents/*.mdGlob for ~/.config/opencode/agents/*.mdAskUserQuestion:Read the selected agent file and store its contents.
Spawn the researcher agent to check latest documentation:
Task:
subagent_type: "agent-alchemy-opencode-tools:oc-researcher"
prompt: |
Research the latest OpenCode documentation for agent format compatibility.
Artifact type: agent
Current artifact content:
---
{contents of the agent file}
---
Specific questions:
1. Are there any new agent frontmatter fields?
2. Have permission syntax rules changed?
3. Are there new agent modes or capabilities?
4. Any changes to subagent behavior or limitations?
Reference guide: ${CLAUDE_PLUGIN_ROOT}/references/agent-guide.mdCompare the existing agent against current best practices:
| Issue | Detection | Fix |
|---|---|---|
name field present | Should not exist — name from filename | Remove |
skills field present | Skills not assignable to agents | Remove |
Invalid mode value | Must be primary, subagent, or all (default: all) | Fix or default to all |
| Wrong model format | Must be provider/model-id | Convert |
| Temperature out of range | Must be 0.0-1.0 | Clamp to valid range |
top_p out of range | Must be 0.0-1.0 if present | Clamp to valid range |
| Invalid permission syntax | Values must be allow/ask/deny/true/false | Fix syntax |
Missing description | Required field | Add based on agent content |
| Issue | Detection | Fix |
|---|---|---|
Subagent uses question | Subagents can't use question tool | Add note or restructure |
| Claude Code tool names | AskUserQuestion instead of question | Convert to OpenCode names |
mcp__ format | Double-underscore MCP naming | Convert to single-underscore |
${CLAUDE_PLUGIN_ROOT} refs | Claude Code path variable | Remove or convert |
| Missing purpose statement | No clear first sentence | Add purpose statement |
| No output format section | Agent should specify output | Add output format |
| Issue | Detection | Fix |
|---|---|---|
| Glob pattern syntax errors | Invalid patterns in permission rules | Fix syntax |
| Overly permissive subagent | Subagent with full write/bash access | Suggest tightening |
| Missing common tools | No read/glob/grep permissions set | Add basic permissions |
Present the analysis organized by severity:
## Update Analysis: {agent-name}
### Errors (must fix)
{list with explanations}
### Warnings (should fix)
{list with explanations}
### Suggestions
{list with explanations}
### Research Notes
{findings from researcher agent}Use AskUserQuestion for approval:
Apply changes based on user selection:
Edit to modify the agent fileSpawn the validator agent:
Task:
subagent_type: "agent-alchemy-opencode-tools:oc-validator"
prompt: |
Validate the following OpenCode artifact:
Type: agent
Path: {path to updated file}
Reference guide: ${CLAUDE_PLUGIN_ROOT}/references/agent-guide.mdPresent validation results and a before/after summary of changes.
CRITICAL: Complete ALL 7 phases before finishing.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.