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-plangit 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-plan)<a href="https://agentmods.dev/skills/zaxbyhub/opencode-swarm/swarm-plan"><img src="https://agentmods.dev/badge/skills/zaxbyhub/opencode-swarm/swarm-plan/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-plan"><img src="https://agentmods.dev/badge/skills/zaxbyhub/opencode-swarm/swarm-plan.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 Excessive Agency · line 238 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00032 | $0.06582 |
| Opus 5 | $0.00016 | $0.03291 |
| Sonnet 5 | $0.00006 | $0.01316 |
| Haiku 4.5 | $0.00003 | $0.00658 |
Grade A, and why
swarm-plan 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 4d 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 — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Protocol
This protocol is loaded on demand by the architect runtime. The architect prompt keeps only activation, action, and hard safety constraints; the full execution details live here.
Graph-first evidence contract
Before planning, call repo_map with graph_health, then package_boundaries and key_files, followed by a targeted source-bearing context_pack. Graph evidence is advisory only. If freshness is stale or inconclusive, confidence is low, source is missing, the language is unsupported/dynamic, the graph is absent, or an action fails, inspect the direct source and searches before committing the plan.
MODE: PLAN
PLANNING PROFILE (authoritative): obey the runtime-injected [PLANNING PROFILE — AUTHORITATIVE] directive, which is produced by the same resolver used by
save_plan. Select exactly one path:
balanced: use durable QA/execution defaults and do not pause for the full questionnaire, spec ceremony, or complete clarification funnel. Ask only for unresolved material ambiguity, destructive/high-risk authorization, or a decision only the user can make.save_planexact-binds the default QA profile. Persistplanning_profile: "balanced".strict(including locked legacy profiles with no stored field): require an effective spec, run the complete clarification funnel, present the unified QA/execution questionnaire, and wait for the user's answers before saving. Persistplanning_profile: "strict"only when the field is already explicit or this is a new/unlocked plan; do not materialize it into a locked legacy profile.
A locked profile may ratchet balanced to strict; it never moves strict to
balanced.
SPEC POLICY (profile-dependent — check before planning):
An effective spec exists iff /swarm sdd status reports a resolved spec (it reflects readEffectiveSpecSync, which returns null for no sources, multiple competing sources, multi-feature Spec-Kit without a selected feature, or any unresolvable state). Do NOT enumerate these cases — defer to /swarm sdd status.
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.
- 4d ago First seen · 337 lines · 32 tokens per session scan A 758ff085fc80
swarm-plan is a skill published in the GitHub repository ZaxbyHub/opencode-swarm (466 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 6,582 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 2026-09-05.
Other skills, from other repositories
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.
businesses
Business lifecycle skill (DOMAIN-AGNOSTIC). Creates, lists, inspects, validates, and migrates businesses — autonomous multi-agent organizations — following the Business Protocol v2 (v1 businesses still load unchanged). Works for ANY domain: marketing, healthcare, engineering, legal, real-estate, gaming, foodtech…
nirvana-os
List and inspect the user's Nirvana-OS businesses (empresas), squads and mind-clones, and route production briefs to the harness orchestrator. Trigger on 'quais são minhas empresas/squads', 'what businesses/squads do I have', 'liste minhas empresas', 'quais mind-clones eu tenho', 'o que o nirvana pode fazer', 'use o…
beads-schema
Beads (bd CLI) reference — issue types, statuses, priorities, dependencies, and common commands.
trelly-mcp
Configure and use the trelly MCP stdio server (trelloboardslist, trellocardcreate, trellosearch, trelloapiget, etc.). Use when wiring Cursor/Claude MCP, listing or showing Trello cards/todos, linking GitHub PRs/commits, or choosing MCP vs CLI.
trelly
Operate the trelly Trello CLI (npm trelly; bin trelly): auth setup/login, human vs --json output, boards/lists/cards, search, attachments, GitHub PR/commit links on cards, trelly ui, trelly api. Use when the user asks to run trelly commands, list or show Trello cards/todos, link a GitHub PR or commit to a card, or…