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 skills/gutomec/nirvana-os-engine/squadsnpx skills add gutomec/nirvana-os-engine --skill squadsgit clone --depth 1 https://github.com/gutomec/nirvana-os-engineWrote 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/gutomec/nirvana-os-engine/squads)<a href="https://agentmods.dev/skills/gutomec/nirvana-os-engine/squads"><img src="https://agentmods.dev/badge/skills/gutomec/nirvana-os-engine/squads.svg" alt="Measured on agentmods" 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 | $0.00099 | $0.05861 |
| Opus 5 | $0.00049 | $0.02930 |
| Sonnet 5 | $0.00020 | $0.01172 |
| Haiku 4.5 | $0.00010 | $0.00586 |
Grade D, and why
squads scanned grade D with 2 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 today.
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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- `*squad activate {name} --confirm-heavy` — auto-accept downloads >1 GB, sudo installs, and installers that fetch a remote script and execute it Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
**Lifecycle:** Outputs are intermediate. User moves final deliverables to their project structure. Old runs can be cleaned: `rm -rf .squads-outputs/{squad}/{old-run}/` The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 files 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.
- adapters/_template-adapter.md 6.5 KB
- agents/squad-activator.md 9.9 KB
- BUILD-NOTES-V5.md 6.1 KB
- CONFIGURATION.md 12 KB
- lib/activator.js 45 KB runs code
- lib/adapter-loader.js 5.1 KB runs code
- lib/capability-validator.js 15 KB runs code
- lib/compatibility-checker.js 6.5 KB runs code
- lib/discovery.js 8.9 KB runs code
- lib/display-formatter.js 11 KB runs code
- lib/mechanical-fixers.js 31 KB runs code
- lib/migrate-batch-orchestrator.ts 4.7 KB runs code
- lib/migrate-v4-to-v5.js 11 KB runs code
- lib/output-resolver.js 7.1 KB runs code
- lib/registry.js 18 KB runs code
- lib/squad-audit-consensus.js 17 KB runs code
- lib/squad-audit-criteria.js 28 KB runs code
- lib/squad-audit-verifier.js 4.8 KB runs code
- lib/squad-doctor.ts 9.9 KB runs code
- lib/v4-capability-inferrer.js 14 KB runs code
- lib/workflow-reader.ts 33 KB runs code
- README.md 12 KB
- references/01-discovery.md 3.0 KB
- references/02-creation.md 16 KB
- references/03-validation.md 4.6 KB
- references/04-activation.md 6.9 KB
- references/05-schemas.md 5.5 KB
- references/06-workflows.md 5.0 KB
- references/07-execution.md 5.4 KB
- references/08-runtime-contract.md 5.5 KB
- references/09-upgrade.md 7.8 KB
- references/10-context-engineering.md 4.5 KB
- references/11-adapters-guide.md 7.4 KB
- references/12-v5-capabilities.md 9.5 KB
- references/13-v5-registry.md 7.7 KB
- references/15-creation-wizard.md 7.2 KB
- references/cc-squad-standard.md 1.6 KB
- scripts/activate-squad.cmd 540 B runs code
- scripts/activate-squad.ts 4.4 KB runs code
- scripts/audit-batch-orchestrator.ts 7.1 KB runs code
- scripts/audit-squads-score.cmd 286 B runs code
- scripts/audit-squads-score.ts 4.2 KB runs code
- scripts/brief-squad.ts 8.8 KB runs code
- scripts/fix-squad.ts 2.3 KB runs code
- scripts/improve-squad.cmd 271 B runs code
- scripts/improve-squad.ts 11 KB runs code
- scripts/index-squads.cmd 532 B runs code
- scripts/index-squads.ts 2.0 KB runs code
- scripts/init-squad.ts 9.0 KB runs code
- scripts/list-squads.cmd 528 B runs code
- scripts/list-squads.ts 1.9 KB runs code
- scripts/migrate-squad.ts 39 KB runs code
- scripts/validate-squad.cmd 396 B runs code
- scripts/validate-squad.ts 8.6 KB runs code
- SQUAD_PROTOCOL_V4.md 58 KB
- SQUAD_PROTOCOL_V5.md 42 KB
- SQUAD_PROTOCOL_V6.md 38 KB
- SQUAD_PROTOCOL.md 19 KB
- templates/agent-cc.md.tmpl 307 B
- templates/agent.md.tmpl 883 B
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.
- today Changed 6ca078575dab
- 4d ago First seen · 363 lines · 99 tokens per session scan D 8644515ced33
squads is a skill published in the GitHub repository gutomec/nirvana-os-engine (68 stars, last pushed today), with no licence file. It adds 99 tokens to every session and 5,861 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it D with 2 findings (asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
sparc-methodology
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration.
hive-mind-advanced
Advanced Hive Mind collective intelligence system for queen-led multi-agent coordination with consensus mechanisms and persistent memory.
stream-chain
Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows.
red-team-tribunal
Multi-agent adversarial verification system. Use when you need thorough code review, security auditing, or quality validation. Spawns three specialized agents (Skeptic, User Proxy, Optimizer) that must reach consensus before code can be approved.
meta-ads-manager
Meta Ads (Facebook & Instagram) campaign management — creating campaigns, managing budgets, audience targeting, ad creative strategy, A/B testing, and performance optimization. This skill should be used when the user asks to create, manage, analyze, or optimize Facebook or Instagram ad campaigns, or needs ad strategy…
cli-builder
Guide for building TypeScript CLIs with Bun. Use when creating command-line tools, adding subcommands to existing CLIs, or building developer tooling. Covers argument parsing, subcommand patterns, output formatting, and distribution.