vsetchinfc/agistra.dev

agent-foundations

Universal guardrails loaded by every agent. Defines Verify Before Reporting (VBR), Write-Ahead Log (WAL), and the security baseline. Always-on, role-independent.

code-review-and-quality

Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.

documentation-and-adrs

Records decisions and documentation. Use when making architectural decisions, changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.

dreaming

Use when: Good night Team, EOD, Wrapping up, or end-of-day consolidation. Archives session context, promotes durable patterns, and compacts live agent memory files for the next session.

skill-quality-review

Review Codex/Claude agent skills, profile manifests, and skill-related deploy changes before they ship. Use when creating, editing, importing, installing, or reviewing SKILL.md files, agent manifests, optional third-party skills, or plugin skill bundles.…

ticket-lifecycle-mode

Use when: ticket lifecycle, state transitions, ready for QA, changes requested, QA passed, role-based workflow policy, Developer to QA handoff, or relay routing across delivery agents.

architecture-mode

Use when: architecture mode, architect this, ADR, C4, PlantUML, system boundary, design decision, PRD gap, high ambiguity, multiple technical approaches, security architecture, data architecture, integration risk, implementability gap, story ticket, or epic…

token-economics

Token budgeting discipline for all agents. Treats tokens as a resource from session start — not just when the buffer hits 60%. Covers prompt compression, context hygiene, handoff packing, and HOT memory pruning.

external-skill-intake

Use when: 'intake this repo/skill', 'evaluate external skill', 'should we adopt X', a candidate repo URL plus an adoption question, or any external skill/workflow/tool surfaces as a possible fit for Agistra. Structured front-door evaluation of external…

migration-completeness-check

Use when the team lead points Architect at a prior agistra.dev hub path and asks it to check for or perform additional migration — trigger phrasing such as 'migrate my data from <path>', 'check what didn't get migrated', 'did we miss anything from my old…

external-skill-intake

Use when: 'intake this repo/skill', 'evaluate external skill', 'should we adopt X', a candidate repo URL plus an adoption question, or any external skill/workflow/tool surfaces as a possible fit for Agistra. Structured front-door evaluation of external…

migration-completeness-check

Use when the team lead points Architect at a prior agistra.dev hub path and asks it to check for or perform additional migration — trigger phrasing such as 'migrate my data from <path>', 'check what didn't get migrated', 'did we miss anything from my old…

qa-ticket-workflow

Use when: Tester runs a full QA session, processes a Builder handoff, executes test steps, writes a GitHub test report, or aligns ticket state after verification.

task-automation-flow

Use when: 'do work', 'dispatch builder', or team lead triggers automated task implementation. Governs end-to-end flow from dispatch through verification, fail handling, batch mode, and escalation.

telegram-relay

Use when: Router bridges your team and the remote team across Telegram. Classifies inbound messages from the remote agent, dispatches Builder or Tester as subagents, composes replies, and posts outbound state-change notifications.

security-audit-lens

Use when: a general codebase assessment, pre-migration/pre-rewrite review, or explicit security-focused request needs a structured, repeatable security audit pass covering hardcoded secrets, injection-prone constructs, auth/debug backdoors, and insecure…

ui-audit-lens

Use when: UI standards discovery, UI pattern research, UI audit, pre-handoff UI state coverage review, or when a business-specific child skill needs a stack-agnostic UI methodology to load first.

grill-with-docs

One-question-at-a-time design interrogation. Use when: 'grill me', 'interrogate this', 'one question at a time', 'brainstorm', 'let's brainstorm', 'let's discuss', or design review start. Produces ADRs and glossary as decisions settle. Do not use for settled…

security-audit-lens

Use when: a general codebase assessment, pre-migration/pre-rewrite review, or explicit security-focused request needs a structured, repeatable security audit pass covering hardcoded secrets, injection-prone constructs, auth/debug backdoors, and insecure…

ui-audit-lens

Use when: UI standards discovery, UI pattern research, UI audit, pre-handoff UI state coverage review, or when a business-specific child skill needs a stack-agnostic UI methodology to load first.

assumptions-audit

Use when: assumptions audit, audit assumptions, check for hidden assumptions, plan/ticket has ambiguous scope edges, pre-flight before finalizing a ticket, unstated assumptions, or 'what am I assuming'. Surfaces unstated assumptions, ambiguous scope edges,…

assumptions-audit

Use when: assumptions audit, audit assumptions, check for hidden assumptions, plan/ticket has ambiguous scope edges, pre-flight before finalizing a ticket, unstated assumptions, or 'what am I assuming'. Surfaces unstated assumptions, ambiguous scope edges,…

software-engineer-mode

Use when: implement a scoped ticket, fix a bug, add tests, prepare a PR-ready code change, or reuse a standard builder workflow across software engineer agents.

grill-with-docs

One-question-at-a-time design interrogation. Use when: 'grill me', 'interrogate this', 'one question at a time', 'brainstorm', 'let's brainstorm', 'let's discuss', or design review start. Produces ADRs and glossary as decisions settle. Do not use for settled…

frontend-design

Activate for any ticket that builds new UI, reshapes an existing interface, or requires visual direction. Guidance for distinctive, intentional visual design, aesthetic direction, typography, and layout choices. Do not apply when the project has an…

skill-development

Use when: writing or reviewing a SKILL.md file, improving skill descriptions, organizing skill content, or needing guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.

research-analyst

Analytical methodology skill for intelligence-grade research. Covers cognitive security, logical fallacy detection, source epistemology, and probability discipline. Load when evaluating sources, building analytical assessments, or detecting manipulation in…

browser-automation

Use when: Tester needs UI state evidence for VBR, or Builder needs to verify an integration wire is observable end-to-end. Powered by agent-browser MCP — token-efficient browser automation (200–400 tokens/page).

consultant

Writing skill for freelancers and independent consultants. Covers project proposals, bids, client emails, and scope summaries. Leads with the client's problem, not the consultant's background.

debugging-and-error-recovery

Guides systematic root-cause debugging. Use when tests fail, builds break, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need a systematic approach to finding and fixing the root cause rather than guessing.

internal-relay

Workflow-state classification vocabulary for inter-team relay. Maps inbound signals from the remote agent to a routing decision. Intentionally narrow — states and destinations only.

job-seeker

Use when: writing or reviewing cover letters, recruiter email replies, LinkedIn outreach, or interview follow-ups. Removes AI-template patterns and writes with a specific, confident, human voice.

morning-standup

Use when: Good morning Team, start-of-day briefing, or morning status request. Architect orchestrates; Builder, Tester, and Router return their sections as subagents.

proactive-agent

Context-survival and proactive-iteration extensions. Always-on. Covers Working Buffer Protocol, Compaction Recovery, Relentless Resourcefulness, and Self-Improvement Guardrails.

scan-anl

Use when: analysing a project's delivery health — CI/CD, commit patterns, and working tree state.

scan-dbg

Use when: analysing a project's debug and reliability health — inline markers, logging hygiene, and error handling.

scan-sys

Use when: analysing a project's architecture, structure, and infrastructure health from the System perspective.

scan-tst

Use when: analysing a project's test health — coverage, robustness, and CI integration.

scan-usr

Use when: analysing a project's user-facing health — discoverability, documentation, and product clarity.

self-improving-agent

Use when: the agent captures a correction from the team lead, hits an unexpected error, discovers a capability gap, or finds a better practice. Logs to .learnings/ and promotes durable patterns to permanent project memory.