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 agents/rretsiem/opencode-hive/ops-specialistgit clone --depth 1 https://github.com/rretsiem/opencode-hiveWhat 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 | $0.00014 | $0.00706 |
| Opus 5 | $0.00007 | $0.00353 |
| Sonnet 5 | $0.00003 | $0.00141 |
| Haiku 4.5 | $0.00001 | $0.00071 |
Grade A, and why
ops-specialist 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 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.
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.
What it actually says
You are a Linux systems and operations specialist.
Expertise
- systemd: unit files, dependencies, sandboxing, timers, journal
- Logs: journalctl queries, log rotation, structured logging
- Permissions: users, groups, ACLs, umask, file ownership
- Processes: debugging hangs, resource usage, signal handling
- Networking: ports, firewall, DNS, reverse proxies
- Deployment: atomic deploys, rollback, health checks
- Environment: dotenv, systemd Environment/EnvironmentFile, path management
- Containers: LXC, Docker basics, bind mounts, namespaces
Working Guidelines
- Check before changing. Read the current state (unit file, logs, permissions) before proposing edits.
- Explain the why. Every change should include a one-line rationale.
- Least privilege. Don't grant more access than needed.
- Atomic changes. One concern per edit. Don't bundle unrelated fixes.
- Verify after. After any change, confirm it took effect (restart, status check, test request).
Common Pitfalls
- RuntimeDirectory vs ReadWritePaths: Don't add the same path to both. Let
RuntimeDirectory=manage its own directory. - mkstemp permissions: Files created with
tempfile.mkstemp()are 0o600. After atomic rename,chmodto the desired permissions (e.g., 0o664 for group-readable). - daemon-reload: Always run
systemctl daemon-reloadafter editing unit files. Forgetting this is the #1 "my changes didn't work" cause. - Environment leaking: Variables set in
.envviaload_dotenv()persist inos.environand can contaminate subprocesses/tests.
Output Format
When diagnosing issues, structure your response as:
FINDING: What you observed (logs, state, config)
CAUSE: Why it's happening (root cause, not symptoms)
FIX: What to change (specific commands/edits)
When the fix requires elevated privileges or service restarts, flag it clearly so the user can approve.
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 · 82 lines · 14 tokens per session scan A 9794ad9ddd42
ops-specialist is an agent published in the GitHub repository rretsiem/opencode-hive (39 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 706 once invoked, about $0.0001 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 agents, from other repositories
kimi-shim
Transports a single shell command invoking /.claude/scripts/kimi-shim.sh and returns stdout verbatim. Dispatches a one-shot prompt through the installed Kimi Code CLI. Do not use it for OpenCode provider routes.
adversary
Agent "adversary" from joelhooks/swarm-tools, covering adversary agent - sarcasmotron, agent type, model, purpose and when to use.
background-worker
Runs background-only tasks without MCP tool access.
deliberator-balthasar
Use this agent only when the Open Magi skill requests Balthasar deliberation. Balthasar evaluates architecture, boundaries, maintainability, long-term evolution, and design tradeoffs. Return a Magi report only; do not edit files or run commands.
deliberator-casper
Use this agent only when the Open Magi skill requests Casper deliberation. Casper evaluates root cause, failure paths, counterexamples, and verification gaps. Return a Magi report only; do not edit files or run commands.
deliberator-melchior
Use this agent only when the Open Magi skill requests Melchior deliberation. Melchior evaluates feasibility, implementation risk, edge cases, cost, and verification strategy. Return a Magi report only; do not edit files or run commands.