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.
/plugin marketplace add atretyak1985/swarmerynpx agentmods add plugins/atretyak1985/swarmery/coregit clone --depth 1 https://github.com/atretyak1985/swarmeryGrade A, and why
core 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.
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 it installs
The manifest is a name and a version. 3 commands, 42 agents travel with it, and installing the plugin installs all of them — 1,322 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Command code-quality A 12 tokens
- Command deps-check A 7 tokens
- Command dashboard C 15 tokens
- Agent tech-lead A 38 tokens
- Agent code-auditor A 114 tokens
- Agent implementation-agent A 41 tokens
- Agent founder-reality-check A 48 tokens
- Agent implementation-planner A 26 tokens
- Agent task-planner A 26 tokens
- Agent architecture-designer A 27 tokens
- Agent context-gatherer A 23 tokens
- Agent database-designer A 38 tokens
- Agent debugger A 18 tokens
- Agent downstream-analyzer A 36 tokens
- Agent full-stack-feature A 20 tokens
- Agent migration-helper A 17 tokens
- Agent performance-optimizer A 21 tokens
- Agent prompting-agent A 25 tokens
- Agent quality-checker A 62 tokens
- Agent react-specialist A 24 tokens
- Agent retrospective-agent A 24 tokens
- Agent security-auditor A 43 tokens
- Agent silent-failure-hunter A 23 tokens
- Agent sprint-review A 40 tokens
- Agent sre-orchestrator A 34 tokens
- Agent summary-generator A 31 tokens
- Agent task-documenter A 20 tokens
- Agent tech-researcher A 30 tokens
- Agent test-runner A 28 tokens
- Agent test-writer A 25 tokens
- Agent ui-designer A 37 tokens
- Agent verification-agent A 27 tokens
- Agent api-designer A 29 tokens
- Agent build-error-resolver A 23 tokens
- Agent ci-incident-responder A 21 tokens
- Agent contract-validator A 46 tokens
- Agent guardrail-checker A 34 tokens
- Agent performance-monitor A 15 tokens
- Agent plan-reviewer A 24 tokens
- Agent post-task-completion A 21 tokens
- Agent task-decomposer A 15 tokens
- Agent commit-message A 22 tokens
- Agent system-improver A 42 tokens
- Agent migration-agent A 14 tokens
- Agent pr-generator A 16 tokens
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 · 10 lines scan A db3b8c9b2d8d
core is a plugin published in the GitHub repository atretyak1985/swarmery (4 stars, last pushed 8d ago), with no licence file. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.
Other plugins, from other repositories
axiom-git
Composes Conventional Commits messages with gitmoji from the staged diff, deciding type, scope, emoji, subject, and body, and gating on protected branches, staged secrets, and pre-commit hooks.
axiom-versioning
Audits and updates external versioned dependencies across application, infrastructure, and CI/CD configurations.
claudit
Audit and optimize your Claude Code configuration. Caches current Claude Code ecosystem knowledge so any subsequent agent task — building a skill, configuring an MCP, authoring CLAUDE.md — can read it instead of re-fetching docs.
fakoli-crew
Nine specialist AI agents for software engineering — generalist roles (polyglot architect, code reviewer, security auditor, researcher, plugin engineer, integration specialist, documentation writer, infrastructure keeper, QA validator) with TDD enforcement, systematic debugging, and verification gates. Plugin-surface…
fakoli-plugin-critic
Five specialist critic agents for Claude Code plugin development — agent-critic (frontmatter/color/tools), skill-critic (lazy-loading/no-fuzzy-detection), hook-critic (contract-aware/${CLAUDEPLUGINROOT}), mcp-critic (schema/actor-validation), structure-critic (manifest/CHANGELOG/version-sync). Audit any plugin (your.
anvil-pulse
Live operator dashboard for long autonomous anvil runs: claims, phases, lease countdowns, event feed, and stuck-state detection served as a local web page, plus an optional Claude Code statusline segment.