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/acpnpx skills add agentic-control-plane/codex-acp-plugin --skill acpgit clone --depth 1 https://github.com/agentic-control-plane/codex-acp-pluginWhat 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 | $0.00021 | $0.01265 |
| Opus 5 | $0.00010 | $0.00633 |
| Sonnet 5 | $0.00004 | $0.00253 |
| Haiku 4.5 | $0.00002 | $0.00127 |
Grade B, and why
acp scanned grade B with 3 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 2d 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.
mkdir -p ~/.acp && echo "THE_TOKEN" > ~/.acp/credentials && chmod 600 ~/.acp/credentials Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf ~/.acp Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sf -X GET "https://api.agenticcontrolplane.com/govern/health" && echo " — ACP reachable" How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic Control Plane (ACP)
ACP is the identity and governance layer for Codex. When active, every shell command is logged and governed through the user's ACP workspace before it executes. The user does not need to change how they work — ACP runs transparently via a PreToolUse hook.
Honest coverage note: Codex currently fires PreToolUse for Bash/shell commands only — file edits, web fetches, and MCP tool calls do not pass through the hook. Shell is where the blast radius lives (deploys, deletes, git, package publishing), so this still governs the actions that matter most; full-surface coverage arrives as Codex extends its hook events.
What ACP does
- Audit logging — every tool call is recorded with identity, tool name, arguments, timestamp, and decision
- Policy enforcement — workspace admins can allow/deny tool calls by pattern, scope, or ABAC rules
- Rate limiting & budgets — cap tool calls per minute, per month, or by cost
- Content scanning — detect and optionally redact PII in tool inputs
- Team governance — multiple members per workspace, role-based access
ACP does NOT proxy or replace the user's tools. Their MCP servers, Bash commands, and file operations work exactly as before. ACP observes and governs the orchestration layer.
Setup flow — help users connect
When a user asks to set up ACP, connect to ACP, or enable governance, follow these steps:
Step 1: Check if already configured
cat ~/.acp/credentials 2>/dev/null && echo "ACP credentials found" || echo "No ACP credentials"
If credentials exist, skip to Step 4 (verify).
Step 2: Create account or log in
Open the browser to the ACP authorization page:
open "https://cloud.agenticcontrolplane.com/plugin/authorize"
Tell the user:
I've opened your browser to log in to ACP. If you don't have an account, you can sign up there with Google or email. After logging in, you'll see a token — please paste it here.
Step 3: Store credentials
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.
- 2d ago First seen · 132 lines · 21 tokens per session scan B bab1a5e10209
acp is a skill published in the GitHub repository agentic-control-plane/codex-acp-plugin (1 stars, last pushed 18d ago), licensed MIT. It adds 21 tokens to every session and 1,265 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 3 findings (asks for root, recursive force delete, makes network calls). 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）.