samaara-toolkit

Plugin samaara-toolkit from marketplace agent-ops-kit in Samaara-Das/agent-ops-kit. Commands read from the repo's manifest — 1 month ago.

Skills (15)

• canary

  Post-deploy canary monitoring. Watches the live app for console errors, performance regressions, and page failures; takes periodic screenshots, compares against pre-deploy baselines, and alerts on anomalies. Use when asked to "monitor the deploy", "canary", "post-deploy check", "watch production", o

• codex

  OpenAI Codex CLI wrapper — a second opinion from a different model. Three modes. Review: independent diff review with a pass/fail gate. Challenge: adversarial mode that tries to break your code. Consult: ask Codex anything with follow-ups. Use when asked to "codex review", "codex challenge", "ask co

• cso

  Chief Security Officer mode — infrastructure-first security audit: secrets archaeology, dependency supply chain, CI/CD pipeline security, LLM/AI security, OWASP Top 10, STRIDE threat modeling, and active verification. Two modes: daily (zero-noise, 8/10 confidence gate) and --comprehensive (2/10 bar,

• design-review

  Designer's-eye QA on a live site: visual inconsistency, spacing, hierarchy problems, AI-slop patterns, and slow interactions — then fixes them in source with atomic commits and before/after screenshots. Use when asked to "audit the design", "visual QA", "check if it looks good", or "design polish".

• harness-picker

  Picks the right execution HARNESS for a piece of work — plain agent, a single subagent, an agent TEAM (named teammates coordinating live), the multi-agent `Workflow` tool, `/goal`, `/loop`, or `/schedule` — and hands off to set it up. Use this whenever the user is deciding HOW TO RUN something rathe

• investigate

  Systematic debugging with root cause investigation. Four phases: investigate, analyze, hypothesize, implement. Iron Law: no fixes without root cause. Use when asked to "debug this", "fix this bug", "why is this broken", "investigate this error", or "root cause analysis". Proactively invoke this skil

• land-and-deploy

  Land and deploy workflow. Merges the PR, waits for CI and the deploy, then verifies production health with canary checks. Use when asked to "merge", "land", "deploy", "merge and verify", "land it", or "ship it to production". Takes over after the ship skill has created the PR.

• office-hours

  YC office-hours partner — two modes. Startup mode: forcing questions that expose demand reality, the status quo competitor, desperate specificity, the narrowest wedge, observation, and future-fit. Builder mode: design-thinking brainstorm for side projects, hackathons, learning, open source. Produces

• plan-design-review

  Designer's-eye plan review — interactive, before implementation. Rates each design dimension 0-10, explains what would make it a 10, then fixes the plan to get there. Use when asked to "review the design plan", "design critique on the plan", or before building any UI/UX-heavy feature. For auditing a

• plan-eng-review

  Eng-manager-mode plan review. Locks in the execution plan — architecture, data flow, edge cases, test coverage, performance — walking through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", "eng review", or "lock in the plan".

• qa-only

  Report-only QA testing. Systematically tests a web application and produces a structured report with screenshots, severity ratings, and a health score — WITHOUT fixing anything. Use when asked to "qa-only", "test but don't fix", "audit this site", "give me a QA report", or when the tester shouldn't

• qa

  Systematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs", "test and fix", or "fix what's broken". Proactively suggest when the

• review

  Pre-landing PR review. Analyzes the branch diff against the base branch for SQL safety, race conditions, LLM trust boundary violations, shell injection, and other structural issues tests don't catch — then fixes findings, not just lists them. Use when asked to "review this PR", "code review", "pre-l

• ship

  Ship workflow: merge the base branch, run tests on merged code, review the diff, bump the version, update the changelog, commit in bisectable chunks, verify, push, and open a PR. Use when asked to "ship", "ship it", "open a PR", "get this branch ready to merge", or when a feature is done and needs t

• simplicity-lens

  A decision lens for anywhere complexity quietly accretes — what to take on at all, how big to let it get, and how to make it absorbable by other people. Eight forcing questions distilled from Varun Mayya's talk "How Simplifying Everything Makes You Rich": the 70→4 cut, one goal per unit, the iPad te

Similar plugins