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 ZaxbyHub/opencode-swarm --skill swarm-pr-reviewgit clone --depth 1 https://github.com/ZaxbyHub/opencode-swarmWrote 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/zaxbyhub/opencode-swarm/swarm-pr-review)<a href="https://agentmods.dev/skills/zaxbyhub/opencode-swarm/swarm-pr-review"><img src="https://agentmods.dev/badge/skills/zaxbyhub/opencode-swarm/swarm-pr-review/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/zaxbyhub/opencode-swarm/swarm-pr-review"><img src="https://agentmods.dev/badge/skills/zaxbyhub/opencode-swarm/swarm-pr-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Agent Snooping · line 10 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00038 | $0.00263 |
| Opus 5 | $0.00019 | $0.00131 |
| Sonnet 5 | $0.00008 | $0.00053 |
| Haiku 4.5 | $0.00004 | $0.00026 |
Grade A, and why
swarm-pr-review 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 7d 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
Swarm PR Review
Read and follow ../../../.opencode/skills/swarm-pr-review/SKILL.md as the canonical workflow.
Codex Execution Notes
- This adapter is a thin shim only.
- Keep the canonical workflow in
.opencode; do not duplicate protocol text here. - Treat the runtime's parallel-execution capability as the path for one structured exact-six batch; a different dispatch path is not equivalent.
- Treat controller absence as Profile B, not an error: use fresh-context subagents, preserve read-only workflow-lane handling and exact-head provenance, keep
output_refrecovery intact, preserve the PR publication contract, and never report BLOCKED merely because the controller is absent or the only alternative would be a degraded review. - For exact-head provenance, verify the commit with
git rev-parse --verify <full_pr_head_sha>^0andgit cat-file -t <full_pr_head_sha>. - Preserve the canonical workflow reference above so drift checks can verify delegation.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago Changed d56b4dcdffbc
- 11d ago First seen · 19 lines · 38 tokens per session scan A 48523c34f163
swarm-pr-review is a skill published in the GitHub repository ZaxbyHub/opencode-swarm (466 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 263 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 2026-08-30.
Other skills, from other repositories
armada-ledger
Pick the right ledger for a finding. Use when writing defects, adversarial findings, or security findings. Triggers on: ledger, defect, adversarial, security finding, DEF-001, ADV-001, SEC-001.
armada-pr
PR-first finish for a feature lane. Use before reporting a feature done. Triggers on: PR, finish feature, gh pr create, merge, lane complete.
ax-annotation
@AX code annotation workflow skill for agent-driven tag application.
generic-fullstack-code-reviewer
Review full-stack code for bugs, security vulnerabilities, performance issues, accessibility gaps, and CLAUDE.md compliance. Enforces TypeScript strict mode, input validation, GPU-accelerated animations, and design system consistency. Use when completing features, before commits, or reviewing pull requests.
armada-gate
Run an evidence-gate checklist for each success criterion in the current phase. Use when checking if a phase is complete before marking it passed.
atomic-review
Compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", or invokes /atomic-review. Auto-triggers when reviewing pull requests.