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 skills/agentic-control-plane/codex-acp-plugin/acp-connectnpx skills add agentic-control-plane/codex-acp-plugin --skill acp-connectgit clone --depth 1 https://github.com/agentic-control-plane/codex-acp-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/skills/agentic-control-plane/codex-acp-plugin/acp-connect)<a href="https://agentmods.dev/skills/agentic-control-plane/codex-acp-plugin/acp-connect"><img src="https://agentmods.dev/badge/skills/agentic-control-plane/codex-acp-plugin/acp-connect.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.00300 |
| Opus 5 | $0.00012 | $0.00150 |
| Sonnet 5 | $0.00005 | $0.00060 |
| Haiku 4.5 | $0.00002 | $0.00030 |
Grade B, and why
acp-connect scanned grade B 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 4d 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 rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
4. Store the token in `~/.acp/credentials` with `chmod 600` What it actually says
Help the user connect to the Agentic Control Plane.
- Check if
~/.acp/credentialsexists (already configured?) - If not: open
https://cloud.agenticcontrolplane.com/plugin/authorizein the browser - Wait for the user to paste their token
- Store the token in
~/.acp/credentialswithchmod 600 - Verify by hitting
GET https://api.agenticcontrolplane.com/govern/health - Remind them to trust the plugin's hooks (Codex skips plugin hooks until reviewed): they will be prompted, or can review under Codex's hooks settings
- Direct them to
https://cloud.agenticcontrolplane.com/logsto see their audit trail
Keep it conversational and seamless. The user should go from zero to seeing their first logged tool call in under 2 minutes.
After setup, let them know: "Every shell command I run is now logged to your ACP workspace, and your policies decide what needs approval. The ACP MCP tools (acp_cost, acp_audit, acp_optimize, …) also give me your workspace's cost and quality data, so you can ask things like 'what did my agents spend this week?'"
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.
- 4d ago First seen · 20 lines · 24 tokens per session scan B ae548cc8d0cd
acp-connect is a skill published in the GitHub repository agentic-control-plane/codex-acp-plugin (1 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 300 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B 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 skills, from other repositories
safedeps
Gate dependency installs (npm/pip/cargo/go/gem/maven/nuget) with OSV-backed advisory checks, approved-spec ledger, and post-install reorg rollback. Run safedeps check @ before any install command.
docs-sync
Multi-step workflow to audit MCPKernel documentation against the codebase and update README.md, docs/ MkDocs site, CHANGELOG.md. Use when synchronizing documentation with code changes, auditing doc accuracy, or before releases.
test-and-merge
Multi-step workflow to run the full MCPKernel test suite, validate code quality, and merge development branch to main when all checks pass. Use when validating changes, preparing for merge, or checking if development is ready for main.
research-and-improve
Multi-step workflow to research latest MCP security techniques, async Python patterns, sandboxing approaches, and implement improvements to MCPKernel. Use when upgrading architecture, adding new security features, or optimizing performance based on latest research.
search-and-fix
Multi-step workflow to discover issues in MCPKernel and similar repos, implement fixes, and validate with tests. Use when finding and fixing bugs, addressing security gaps, or implementing improvements discovered from issue analysis.
jp-harness-tune
Skill "jp-harness-tune" from Sora-bluesky/ja-output-harness, covering jp-harness-tune — jplint ルールの対話チューニング, 呼び出し方, step 1: 現状の把握, step 2: 操作意図のヒアリング and step 2b: discover フロー（意図 6 の場合）.