Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/TheophilusChinomona/claude-openclaw-pluginWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/theophiluschinomona/claude-openclaw-plugin/oc-structure)<a href="https://agentmods.dev/commands/theophiluschinomona/claude-openclaw-plugin/oc-structure"><img src="https://agentmods.dev/badge/commands/theophiluschinomona/claude-openclaw-plugin/oc-structure/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/theophiluschinomona/claude-openclaw-plugin/oc-structure"><img src="https://agentmods.dev/badge/commands/theophiluschinomona/claude-openclaw-plugin/oc-structure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00015 | $0.00927 |
| Opus 5 | $0.00008 | $0.00464 |
| Sonnet 5 | $0.00003 | $0.00185 |
| Haiku 4.5 | $0.00002 | $0.00093 |
Grade A, and why
oc-structure scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
3. Flag auth files with incorrect permissions (should be chmod 600) Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/oc-structure Command
Inspect the OpenClaw workspace directory layout at ~/.openclaw/.
Arguments
Parse from $ARGUMENTS:
- audit (default): Full workspace structure overview and health check
- agents: List agent workspaces and their contents
- comms: Show communication channels and recent messages
- memory: Inspect memory/lancedb and shared knowledge
Execution
audit (default)
# Show top-level structure
ls -la ~/.openclaw/ 2>/dev/null || echo "~/.openclaw/ not found — run /oc-setup first"
# Show workspace contents
ls -la ~/.openclaw/workspace/ 2>/dev/null
# Count agent workspaces
echo "Agent workspaces:"
ls ~/.openclaw/workspace/agents-workspaces/ 2>/dev/null || echo " (none)"
# Check key files exist
echo ""
echo "Core files:"
for f in openclaw.json models.json workspace/CLAUDE.md workspace/TASKS.json workspace/SPRINT_CURRENT.json workspace/SHARED_KNOWLEDGE.json workspace/IMPROVEMENT_BACKLOG.json; do
[ -f ~/.openclaw/$f ] && echo " OK: $f" || echo " MISSING: $f"
done
# Check auth file permissions
echo ""
echo "Auth file permissions:"
find ~/.openclaw/workspace/agents-workspaces/ -name "auth-profiles.json" -exec stat -c '%a %n' {} \; 2>/dev/null || echo " (no auth files found)"
Present a summary of what exists, what's missing, and any permission issues.
agents
# List all agent workspaces
ls -la ~/.openclaw/workspace/agents-workspaces/ 2>/dev/null || echo "No agent workspaces found"
# For each agent, show key files
for dir in ~/.openclaw/workspace/agents-workspaces/*/; do
agent=$(basename "$dir")
echo ""
echo "--- $agent ---"
ls "$dir" 2>/dev/null
# Show role from IDENTITY.md first line
head -3 "$dir/IDENTITY.md" 2>/dev/null
done
Present a table of agents with their roles and available files.
comms
# Show communication structure
echo "Communication channels:"
find ~/.openclaw/workspace/comms/ -type f 2>/dev/null || echo " (none)"
# Show broadcast messages
echo ""
echo "Broadcast:"
cat ~/.openclaw/workspace/comms/broadcast.md 2>/dev/null || echo " (no broadcast messages)"
# Show recent inbox messages per agent
for dir in ~/.openclaw/workspace/comms/*/inbox/; do
agent=$(basename "$(dirname "$dir")")
count=$(ls "$dir" 2>/dev/null | wc -l)
[ "$count" -gt 0 ] && echo " $agent inbox: $count message(s)"
done
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 112 lines · 15 tokens per session scan A e9f2be0529a8
oc-structure is a command published in the GitHub repository TheophilusChinomona/claude-openclaw-plugin (2 stars, last pushed 5mo ago), licensed MIT. It adds 15 tokens to every session and 927 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.