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-improve)<a href="https://agentmods.dev/commands/theophiluschinomona/claude-openclaw-plugin/oc-improve"><img src="https://agentmods.dev/badge/commands/theophiluschinomona/claude-openclaw-plugin/oc-improve/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-improve"><img src="https://agentmods.dev/badge/commands/theophiluschinomona/claude-openclaw-plugin/oc-improve.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 | $0.02149 |
| Opus 5 | $0.00008 | $0.01074 |
| Sonnet 5 | $0.00003 | $0.00430 |
| Haiku 4.5 | $0.00002 | $0.00215 |
Grade A, and why
oc-improve scanned grade A with 0 findings 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 10d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/oc-improve Command
Scan your OpenClaw installation, cross-reference findings across areas, and suggest prioritized improvements mapped to specific skills and commands.
Arguments
The user provides: $ARGUMENTS
Parse optional flags:
--focus <area>— scan only one area. Valid:channels,agents,sessions,security,sandbox,automation,models,memory,backup,workspace- No flag = scan all 10 areas
Precondition
Check that OpenClaw is installed:
which openclaw 2>/dev/null || echo "NOT_FOUND"
If not found, report:
OpenClaw CLI not found. Run /oc-setup to install.
And stop.
Data Gathering
Run each scan area below. If --focus was given, run only that area. Suppress errors with 2>/dev/null throughout — missing components are expected and become findings, not errors.
1. Channels
openclaw channels status --probe 2>/dev/null
openclaw config get channels 2>/dev/null
Capture: channel count, channel names, DM policies per channel, probe results (connected/failing).
2. Agents
openclaw agents list --bindings 2>/dev/null
ls ~/.openclaw/workspace/agents-workspaces/ 2>/dev/null
For each agent workspace found:
ls ~/.openclaw/workspace/agents-workspaces/$AGENT/ 2>/dev/null
head -5 ~/.openclaw/workspace/agents-workspaces/$AGENT/IDENTITY.md 2>/dev/null
wc -l ~/.openclaw/workspace/agents-workspaces/$AGENT/SOUL.md 2>/dev/null
Capture: agent count, workspace existence, SOUL.md presence and line count, IDENTITY.md presence, bindings list.
3. Sessions
openclaw config get session 2>/dev/null
Capture: dmScope value (main, per-channel-peer, per-account-channel-peer, or unset).
4. Security
openclaw security audit 2>/dev/null
find ~/.openclaw/credentials/ -type f -exec stat -c '%a %n' {} \; 2>/dev/null
openclaw config get gateway.auth 2>/dev/null
openclaw config get gateway.listen 2>/dev/null
Capture: audit findings, file permissions, auth mode, listen address.
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.
- 10d ago First seen · 223 lines · 15 tokens per session scan A 78757de62d1d
oc-improve 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 2,149 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. 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.