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 sandydasari/openacme --skill openacme-platformgit clone --depth 1 https://github.com/sandydasari/openacmeWrote 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/sandydasari/openacme/openacme-platform)<a href="https://agentmods.dev/skills/sandydasari/openacme/openacme-platform"><img src="https://agentmods.dev/badge/skills/sandydasari/openacme/openacme-platform/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/sandydasari/openacme/openacme-platform"><img src="https://agentmods.dev/badge/skills/sandydasari/openacme/openacme-platform.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 24 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Rogue Agent · line 144 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- medium Output Handling · line 126 Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.Fix: Set explicit limits on output length, generation count, and rate. Use max_tokens and truncation to prevent unbounded output.
- medium Data Exfiltration · line 159 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00066 | $0.04040 |
| Opus 5 | $0.00033 | $0.02020 |
| Sonnet 5 | $0.00013 | $0.00808 |
| Haiku 4.5 | $0.00007 | $0.00404 |
Grade A, and why
openacme-platform 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 9d 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 — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenAcme platform reference
OpenAcme is an AI-workforce platform — a set of role-specialized agents working for a small human team. You are the platform-admin agent. The user asks you to set up other agents, install skills, wire up MCP servers, and explain how things work. This document is your reference for all of that.
Data directory layout
Every install has a single data directory (default ~/.openacme/). The
user can override with OPENACME_DATA_DIR. Layout:
<dataDir>/
├── config.yaml # platform config — top-level model, server port, browser
├── auth.json # OAuth tokens (0600). NEVER touch.
├── .env # provider API keys. NEVER touch.
├── mcp-tokens/ # MCP OAuth state. NEVER touch.
├── state.db # SQLite — sessions, messages, comments, events. NEVER write directly.
├── AGENTS.md # shared workforce context — injected into every agent's prompt
├── mcp.json # global MCP server catalog (inherited by every agent unless disabled)
├── skills/<name>/SKILL.md # workforce-wide skills (you can write these)
├── agents/<id>/
│ ├── AGENT.md # YAML frontmatter + persona body
│ ├── email.json # per-agent mailbox creds (0600). NEVER touch.
│ ├── workspace/ # default cwd for the agent's shell + filesystem tools
│ ├── resources/ # user-supplied reference files (style guides, templates)
│ ├── browser-profiles/ # per-agent browser profile (chromium/ and/or firefox/)
│ └── memory/
│ ├── MEMORY.md # index, always injected into prompt
│ ├── <topic>.md # entry files read on demand
│ └── peers/<id>.md # notes about a coworker, from prior delegations
├── teams/<id>/TEAM.md # team definition (members, manager) + body
├── tasks/<id>.md # one file per task (YAML frontmatter + body)
└── attachments/<sid>/<aid>/<file> # chat file uploads
Each agent runs its own browser (separate profile, separate cookies)
and its own mailbox — both per-agent, never shared. email.json holds
mailbox credentials and is off-limits alongside the other secrets.
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.
- 9d ago First seen · 369 lines · 66 tokens per session scan A 9c5fe5fca169
openacme-platform is a skill published in the GitHub repository sandydasari/openacme (85 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 4,040 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 2026-08-30.
Other skills, from other repositories
hive.browser-automation
Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…
hive.worker-delegation
Concrete patterns for breaking colony work into parallel worker jobs via runplaybook — when fan-out helps, how to model the goal as a tracker table, write the worker skill, author the playbook, pilot, and let convergence retry/resume the gap.
hive.linkedin-automation
Read before automating LinkedIn with browser tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile…
hive.x-automation
Read before automating X / Twitter with browser tools. Verified flows for post, reply, delete, search-and-engage, plus the Draft.js compose quirks that silently disable the send button. Includes the daily-reply and job-market-reply playbooks. Requires hive.browser-automation for the underlying screenshot + coordinate…
test-reporting
Run the Level 2 dummy agent integration test suite and produce a detailed HTML report with per-test input → outcome analysis.
hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…