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.
npx agentmods add commands/darrenhinde/openagentscontrol/oac-statusgit clone --depth 1 https://github.com/darrenhinde/OpenAgentsControlWhat 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 | $0.00016 | $0.00311 |
| Opus 5 | $0.00008 | $0.00156 |
| Sonnet 5 | $0.00003 | $0.00062 |
| Haiku 4.5 | $0.00002 | $0.00031 |
Grade A, and why
oac-status scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Show the current OAC plugin status.
Run:
echo "=== Context Installation ===" && \
cat "${CLAUDE_PLUGIN_ROOT}/.context-manifest.json" 2>/dev/null | grep -E '"profile"|"downloaded_at"|"version"' || echo "Not installed — run /install-context" && \
echo "" && \
echo "=== Context Root ===" && \
cat .oac.json 2>/dev/null || echo "No .oac.json — context root not pinned" && \
echo "" && \
echo "=== Context Files ===" && \
ls "${CLAUDE_PLUGIN_ROOT}/context/" 2>/dev/null | wc -l | xargs -I{} echo "{} component directories installed"
Then report in plain language:
- Plugin version: 1.0.0
- Context status: installed profile + component count, or "not installed"
- Context root: path from
.oac.json, or "not pinned (run /install-context)" - Available skills: install-context, context-discovery, approach, debugger, verification-before-completion, task-breakdown, code-execution, test-generation, code-review, external-research, parallel-execution
- Available subagents: context-scout, task-manager, coder-agent, test-engineer, code-reviewer, external-scout
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.
- yesterday First seen · 26 lines · 16 tokens per session scan A 1f8f73d808ba
oac-status is a command published in the GitHub repository darrenhinde/OpenAgentsControl (4,799 stars, last pushed 17d ago), licensed MIT. It adds 16 tokens to every session and 311 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 2026-08-30.
Other commands, from other repositories
fix
Auto-fix linting, formatting, and common issues.
extract-qa
Extract all Q&A pairs (AskUserQuestion interactions) from the current session.
status
Pipeline status for a spec/feature — or, with no slug, the whole-project delivery report (every spec/backlog/quick-task + GitHub/Linear cross-ref).
webui
Start the Claude Paper web UI.
plan
Run the PO Phase pipeline for a single feature (db-agent → designer-agent → specification-agent).
device-info
扫描设备 + 自动识别芯片型号/VID:PID + 给出驱动建议.