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 formal-report-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/formal-report-openaccp)<a href="https://agentmods.dev/skills/0fuk/openaccp/formal-report-openaccp"><img src="https://agentmods.dev/badge/skills/0fuk/openaccp/formal-report-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/formal-report-openaccp"><img src="https://agentmods.dev/badge/skills/0fuk/openaccp/formal-report-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 | $0.00055 | $0.01643 |
| Opus 5 | $0.00028 | $0.00822 |
| Sonnet 5 | $0.00011 | $0.00329 |
| Haiku 4.5 | $0.00006 | $0.00164 |
Grade A, and why
formal-report-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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Formal Report OpenACCP
Report current state, completed work, unverified claims, blockers, next actions, authority limits, and basis references.
Use owner-readable language. Do not call validator pass semantic approval or reviewer recommendation final acceptance.
Every formal report must carry a Response ID, not Report ID. It must also include a Response log path: line. If there is no persisted log file, write Response log path: chat reply or the project-local status artifact path.
Use the user's preferred language when it is known. If the language is not known, keep the language consistent with the user's current conversation.
When the preferred language is Chinese, use Chinese as the main language for headings, summaries, table cells, evidence explanations, 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 report.
Chat Table Fit Rule
Formal reports are often rendered in narrow chat panes. Keep the table readable:
- Use short first-column labels. Generic reports may use
Changed,Progress,Gate,Area,Goal,Gaps,Next. - Chinese post-install and generic startup reports should use
做了什么,总体进度,验证,范围,目标,缺口,下一步. - Primary Chinese reports should use
做了什么,总体进度,Frontier,目标,缺口,下一步. - Frontier Chinese reports should use
做了什么,总体进度,Lane,目标,缺口,下一步. - Use
类型和状态as the Chinese first-column header. It avoids the/line-break point and keeps the table pure Markdown. - Keep each table cell to a short summary.
- Do not use free-form row labels such as
安装,Skill,CLI,项目,状态,What changed,Lane or area,Next step,Validation, orCheckpoint. - Do not put long paths, URLs, commit hashes, full commands, validation logs, executable paths, local install paths, or long inline-code snippets inside table cells.
- Do not include PowerShell blocks, bash blocks, shell command blocks, command lists, or command dumps anywhere in a chat formal report. Validation evidence should be a short status only, such as
验证通过orValidation passed. - Put only short evidence notes after the table. Chinese reports use
依据与验证; English reports useEvidence and Validation. - Always use the exact table header
| 类型和状态 | 内容 |for Chinese reports or| Item/Status | Content |for English reports. Legacy slash headers, short Chinese headers, mixed status headers, field/content headers, and custom headers are invalid. - Do not use
<nobr>, HTML wrappers, invisible characters, or spacing tricks in formal-report tables. - Keep validation, gate, or checkpoint-like information in the
验证/Gaterow for generic reports or in the evidence section outside the table. The table row set excludesCheckpoint.
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 · 93 lines · 55 tokens per session scan A b1f4c0da0223
formal-report-openaccp is a skill published in the GitHub repository 0fuk/OpenACCP (2 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 1,643 once invoked, about $0.0003 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.