agenthood
ListedA society of AI agents with impeccable standards and zero tolerance for 'fix stuff' commits.
Bundles
Everything this plugin ships — skills, agents, commands, hooks, and MCP servers it bundles.
Skills (60)
accessibility-auditor
Audits web interfaces for WCAG compliance — semantic HTML, ARIA, keyboard navigation, color contrast, screen reader compatibility, and accessible forms. Use when generating or reviewing HTML, or verifying an interface against accessibility standards.
aws
Manage AWS resources via the aws CLI. Use when managing S3, EC2, Lambda, or other AWS services.
bug-fix-teammate
Identifies critical bugs in a codebase and implements targeted fixes with working code — root cause, minimal change, regression tests. Use when a bug needs to be fixed, not just diagnosed.
cleanup-specialist
Removes dead code, eliminates duplication, refactors messy patterns, and applies consistent formatting across code and documentation — safely, with tests before and after. Use when a codebase needs maintainability work without behavior change.
code-review
Conducts multi-axis code review across correctness, readability, architecture, security, and performance. Use before merging any change.
code-smell-detection
Detects code smell, complexity violations, architectural boundary breaches, and dead code. Use for codebase quality scans.
commit-messages
Writes conventional commit messages, PR descriptions, and changelogs from diffs and branch history. Use when staging a commit.
concept-explainer
Breaks down complex technical concepts in beginner-friendly ways with analogies, practical examples, and understanding checks. Use when explaining a technical topic to a learner, onboarding someone into unfamiliar code, or writing educational documentation.
context-economy
Monitors context window capacity, routes tasks to minimal member set, and triggers session triage. Use when managing session capacity.
cross-provider-translation
Detects AI providers, translates skill files to provider-native formats, and validates conventions. Use when onboarding new providers.
datadog
Monitor infrastructure and applications via Datadog API and CLI. Use when querying metrics, logs, or managing monitors.
debugging-and-error-recovery
Diagnoses errors, traces root causes, and guides systematic recovery. Use when encountering any error, failing test, or unexpected behavior.
Show all 60 bundled skills Showing all 60 bundled skills
debugging-tutor
Teaches systematic debugging methodology — reproduction, isolation, hypothesis formation, and independent problem-solving — rather than handing out quick fixes. Use when a learner is stuck on a bug and the goal is to build their own debugging skills.
docker
Manage Docker containers and images via the docker CLI. Use when building, running, or debugging containers.
elasticsearch
Manage Elasticsearch clusters via the REST API. Use when querying, indexing, or managing Elasticsearch indices.
Send emails via SMTP or sendmail. Use when sending transactional emails or notifications programmatically.
github
Manage GitHub repositories via the gh CLI. Use when working with issues, PRs, releases, or repository settings.
gitlab
Manage GitLab repositories via the glab CLI. Use when working with merge requests, issues, or CI/CD pipelines.
goal-refinement
Translates ambiguous goals into structured problem statements, success criteria, and ranked priorities. Use when requirements are vague.
implementation-planner
Creates detailed implementation plans and technical specifications in markdown — feature breakdown, phased tasks with complexity estimates, risks, and success criteria. Use before starting a non-trivial feature to turn requirements into an executable roadmap.
institutional-knowledge
Holds institutional knowledge about members, conventions, and architecture. Use before authoring new members or researching patterns.
issue-manager
Creates well-structured, actionable GitHub issues and manages issue-driven work with clear titles, reproduction steps, and measurable success criteria. Use when filing bug reports, proposing features, or triaging an existing issue queue.
jira
Manage Jira issues, sprints, and epics via the jira-cli. Use when viewing, creating, or updating Jira issues.
kubernetes
Manage Kubernetes clusters via kubectl. Use when deploying, inspecting, or debugging Kubernetes resources.
linear
Manage Linear issues and projects via the linear CLI. Use when viewing, creating, or updating Linear tasks.
mongodb
Manage MongoDB databases via the mongosh CLI. Use when querying, inspecting, or managing MongoDB collections.
mysql
Manage MySQL databases via the mysql CLI. Use when querying, inspecting schema, or managing MySQL databases.
onboarding-plan
Creates personalized, phased onboarding plans for new team members — environment setup, codebase discovery, first contributions, and early wins. Use when a new developer joins the team and needs a structured path from first day to first contribution.
postgres
Manage PostgreSQL databases via the psql CLI. Use when querying, inspecting schema, or managing PostgreSQL databases.
pull-request-assistant
Generates comprehensive pull request descriptions and conducts structured code reviews with security, performance, testing, and documentation focus areas. Use when opening a PR or reviewing one before merge.
redis
Manage Redis via the redis-cli. Use when interacting with Redis caches, queues, or key-value stores.
release-notes
Manages semantic versioning, release notes, changelog generation, and scheduled reports. Use before every release.
remember
Reviews conversation history and captures valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says "remember this", "save what we learned", "update memory", or "capture learnings".
runtime-health
Manages runtime health, deployment, incidents, rollback, and monitoring. Use during deployment verification and incident triage.
security-and-hardening
Reviews code for security vulnerabilities, dependency risks, and access control issues. Use before merging security-sensitive changes.
sentry
Monitor and debug application errors via the Sentry CLI. Use when triaging production errors or managing releases.
society-integrity
Audits member files for internal consistency, cross-member contradictions, and structural drift. Use when validating member structure.
spec-driven-development
Creates structured specifications before coding. Use when starting a new feature, when requirements are unclear, or a design decision needs recording.
telegram
Send messages and manage Telegram bots via the Bot API. Use when sending notifications or building chat interactions.
test-driven-development
Drives test-driven development, generates tests for existing code, and reviews coverage quality. Use before implementing any behavior.
the-architect
Drives spec-first development, task decomposition, and architecture decisions. Use before any non-trivial implementation begins. Use when requirements are unclear, a design decision needs to be recorded, or a feature needs to be broken into implementable tasks.
the-auditor
Reviews code for security vulnerabilities, dependency risks, and access control issues. Use before merging any security-sensitive change, on a regular audit schedule, or when adding new dependencies. The Auditor assumes breach and reads code the way an attacker would.
the-builder
Use when you need coding, implementation, refactoring, patching, or test work; the Builder turns concrete repo context into the smallest verified change and follows local patterns, AGENTS.md, and nearby tests.
the-debugger
Diagnoses errors, traces root causes, and guides systematic recovery. Use when encountering any error, failing test, or unexpected behavior. The Debugger does not guess — it follows a five-step protocol from symptom to root cause.
the-doorman
Validates commit messages, PR titles, branch health, and repository standards. Use to enforce conventions locally and in CI, run health checks, and audit repository hygiene. Nothing gets in without proper credentials.
the-envoy
Detects active AI providers, translates Agenthood skill files to provider-native formats, validates convention enforcement across runtimes, and generates bootstrap configs for new provider onboarding. One Society. Every runtime. No exceptions.
the-herald
Manages semantic versioning, release notes, changelog generation, and scheduled reports. Use before every release to determine the version bump and generate changelog. Use for daily standups and end-of-day summaries.
the-inspector
Solve and generate challenging multimodal visual-reasoning questions involving pixel ranking, cross-panel coordinate mapping, graph-cut side classification, and confidence-bearing answer extraction. Use when the task asks for precise interpretation of low-resolution images, multi-panel figures, or benchmark-style vision questions.
the-librarian
Creates and maintains documentation, READMEs, ADRs, and API references. Use when documentation is missing, outdated, or after code changes that affect documented behavior. The Librarian ensures that knowledge outlives the developer who created it.
the-mailman
Manages message delivery, content scheduling, notification dispatch, and cross-posting across channels. Use before publishing any scheduled content, when configuring notification pipelines, or when setting up cross-platform distribution workflows.
the-operator
Manages runtime health, deployment, incidents, rollback, and monitoring for agenthood services.
the-oracle
Holds institutional knowledge about the Agenthood — member format, naming conventions, layer taxonomy, registration maps, and convention rationale. Ask before authoring a new member, extending the Society, or researching structure. Saves tokens. No exploration required.
the-reviewer
Conducts multi-axis code review across correctness, readability, architecture, security, and performance. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human.
the-scribe
Writes commit messages, PR descriptions, and changelogs from diffs and branch history. Use whenever staging a commit, opening a PR, or preparing a release. The Scribe turns your diff into prose worth reading.
the-sentinel
Audits Agenthood member files for internal consistency, cross-member contradictions, lane overlap, and structural drift against The Oracle's template. The Society cannot enforce standards it no longer understands. The Sentinel makes sure it always does.
the-steward
Monitors context window capacity, routes tasks to the minimal required member set, optimizes member loading for provider-specific caching, and triggers session triage before capacity forces the decision. The Steward was born from the situation it exists to prevent.
the-strategist
Translates ambiguous goals into structured problem statements, success criteria, and ranked priorities before the Architect starts planning. Use when requirements are vague, a feature request needs refinement, or the path from "what" to "how" is unclear. The Strategist fills the gap between "ship this feature" and "here is the spec."
the-tester
Drives test-driven development, generates tests for existing code, and reviews coverage quality. Use before implementing any behavior (write the test first), when generating tests for untested code, or when assessing whether tests actually verify the right things.
the-warden
Detects code smell, complexity violations, architectural boundary breaches, dead code, and dependency decay in project code. Runs on every PR diff and on demand for full codebase scans. The chaos does not arrive all at once — The Warden is here for the accumulation.
validation-and-enforcement
Validates commit messages, PR titles, branch health, and repository standards. Use to enforce conventions and run health checks before merge.
Quality Score: 49/100
Details
- Author
- fworks-tech
- Repository
- fworks-tech/agenthood
- Created
- 3 months ago
- Last Updated
- today
- Language
- TypeScript
- License
- MIT