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 skills add 0fuk/OpenACCP --skill frontier-orchestrator-openaccpgit clone --depth 1 https://github.com/0fuk/OpenACCPWrote 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/0fuk/openaccp/frontier-orchestrator-openaccp)<a href="https://agentmods.dev/skills/0fuk/openaccp/frontier-orchestrator-openaccp"><img src="https://agentmods.dev/badge/skills/0fuk/openaccp/frontier-orchestrator-openaccp/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/skills/0fuk/openaccp/frontier-orchestrator-openaccp"><img src="https://agentmods.dev/badge/skills/0fuk/openaccp/frontier-orchestrator-openaccp.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 | $0.00049 | $0.03135 |
| Opus 5 | $0.00024 | $0.01568 |
| Sonnet 5 | $0.00010 | $0.00627 |
| Haiku 4.5 | $0.00005 | $0.00314 |
Grade A, and why
frontier-orchestrator-openaccp 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontier Orchestrator OpenACCP
Frontier is a lane orchestrator, not a default implementation worker.
Reply Contract
Every Frontier reply must use human-explain-openaccp style in the preferred language. Explain what the lane has proven, what is provisional, what remains missing, what Frontier will do next, and what the human should do next.
If the preferred language is Chinese, Chinese must be the main language for report rows, explanations, evidence summaries, and next actions. Keep English only for stable technical terms and exact names such as Primary, Frontier, worker, reviewer, handoff, validator, source pack, Prompt ID, Response ID, CARD, task-card, B0/B1/B2/B3, CI, CLI, JSON, schema, exact file names, or project-specific product terms. Do not write long English sentences or paragraphs in a Chinese reply.
Every Frontier reply must end with a short Recommended Next Step / 下一步建议 paragraph. If no human action is needed, say that plainly: Recommended next step: none; Frontier will continue B0/B1/B2 lane-local closure. If human input is needed, name the exact decision, path, file, fact, approval, or authority boundary that is missing.
Every status-like Frontier reply must also use formal-report-openaccp structure with the Frontier/Lane row contract and evidence details outside the table. Do not return machine-log prose as the main user-facing answer.
Gap Decisions
Use this gapDecisionMatrix vocabulary for every visible gap:
- do_now
- dispatch_current_thread_subagent
- prepare_package
- prepare_package_only_when_dispatch_unavailable
- apply_conservative_default
- needs_final_authority
- explicitly_out
Authority level: B2 lane-local by default when launched by Primary, unless the prompt record explicitly grants a narrower authority.
Continue B0/B1/B2-safe work while it can reduce risk. Do not claim final acceptance.
Machine Contract
Frontier prompt records should carry this machine-readable contract block, updated only to fill lane-specific values:
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 · 226 lines · 49 tokens per session scan A 64f4b7b52d68
frontier-orchestrator-openaccp is a skill published in the GitHub repository 0fuk/OpenACCP (2 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 3,135 once invoked, about $0.0002 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 skills, from other repositories
coordinate-agents
Route Codex-native multi-agent orchestration in a Git repository through a local-first, recoverable Agent Bus. Use for role-based planning, task execution, review, recovery, adapters, and human-gated release workflows. The plugin supports Codex CLI, Google Antigravity CLI, Claude, and other configured coding agents.…
company-handbook
The cross-director coordination protocol for the 1ai business kingdom. Defines how Content, Video, Image, Marketing, and Sales directors work together. Has memory via 1ai-hub brain, follows 1ai-rules, and coordinates with Vilona (GM). Use when coordinating multiple directors, resolving conflicts between teams, or when…
nexus
Use in repos coordinated by the Nexus CLI, especially when NEXUSCONSTITUTION.md, NEXUSQUEUE.md, NEXUSSTANDUP.md, or .nexus/ exists, or when the user asks about Nexus start/claim/release/doctor/status/next.
handoff-mesh
Built-in communication layer for multi-agent setups. Full-mesh handoff folders (any agent can hand off to any other), an hourly watcher that surfaces open handoffs, weekly archive cleanup, and a completion-reporting loop so every handoff is handled AND verified. The durable 'brain' counterpart to real-time channels…
clawmail
Canonical joelclaw mail coordination protocol for all agents. Use when announcing work, checking inboxes, reserving files, releasing locks, handling task handoffs, triaging stale reservations, or auditing coordination quality. Triggers on: 'clawmail', 'agent mail', 'joelclaw mail', 'reserve files', 'release locks'…
report-issue-local
File a bug or feature request against this MCP server's own repo. Use for server-specific issues — tool logic, service integrations, config problems, or domain bugs that aren't caused by the framework.