iusztinpaul/designing-real-world-ai-agents-workshop
Instructions file CodexOpenCode
Instructions for iusztinpaul/designing-real-world-ai-agents-workshop, a project described as: Hands-on workshop: Build a multi-agent AI system from scratch — Deep Research Agent + Writing Workflow served as MCP servers. Includes code, slides, and video.
iusztinpaul/designing-real-world-ai-agents-workshop
Instructions file
Instructions for iusztinpaul/designing-real-world-ai-agents-workshop, covering project, project structure, tech stack, access documentation and running qa.
iusztinpaul/designing-real-world-ai-agents-workshop
Skill Claude CodeCodex
Harness-agnostic version of /implement. Drives a single workshop ticket through the SWE→Tester loop in ONE conversation, with the role prompts bundled as agents/software-engineer.md and agents/tester.md instead of being launched as subagents. Resolves the ticket from implementyourself/tasks/, creates an…
iusztinpaul/designing-real-world-ai-agents-workshop
Agent Codex
SWE role definition for /implement-universal. Loaded by the orchestrator at the start of the SWE phase. Implements one workshop ticket from implementyourself/tasks/NNN-slug.groomed.md, populates the skeleton under implementyourself/src/, runs make QA + the ticket's e2e target, and produces a hand-off message in the…
iusztinpaul/designing-real-world-ai-agents-workshop
Agent Codex
Tester role definition for /implement-universal. Loaded by the orchestrator at the start of the Tester phase, on logic tickets only. Trusts the SWE phase's happy-path e2e excerpt (does NOT re-run the Make target), runs at most 1 adversarial break path, walks every Acceptance Criterion with concrete evidence, and emits…
iusztinpaul/designing-real-world-ai-agents-workshop
Skill Claude CodeCodex
Drive a single workshop ticket through the inner SWE↔Tester loop. Resolves the ticket from implementyourself/tasks/, creates an implementing/from-scratch branch (a fixed default — not derived from the ticket; subsequent tickets stack on top), launches the software-engineer agent to implement it, then routes by…
Plugin Claude Code
Plugin marketplace listing 1 plugin: squid.
Plugin Claude Code
Opinionated engineering agent team with progressive-disclosure specs for Python / TypeScript / Go monorepos. Ships PA / SWE / Tester / PR Reviewer / On-Call sub-agents, /squid-plan / /squid-implement-task / /squid-implement-night pipelines, and a library of language/framework/infra specs that agents load on-demand.
Instructions file CodexOpenCode
Instructions for iusztinpaul/squid, covering squid: an opinionated software factory for claude code, key principles you will respect all over your work, what's in the repo, editing conventions and companion plugin: caveman (optional).
Instructions file
Instructions for iusztinpaul/squid, a project described as: The Software Factory.
Agent
Monitors CI/CD after git push. If the pipeline fails, identifies the related task from commit messages, reopens it, diagnoses the root cause, and hands a concrete fix task to the SWE — then re-verifies the pipeline turns green once the fix lands. Owns pipeline health; does not change application code itself. Use after…
Agent
Reads the git diff after a feature is pushed, tags every finding as Blocker or Nit, and produces ONE rollup task containing all findings. Does NOT read CI, does NOT merge. Use after the SWE has pushed the feature branch and before the orchestrator hands the PR back to the human for squash-merge.
Agent
Grooms raw tasks into agent-ready specs (acceptance criteria + BDD scenarios) AND does final user-perspective acceptance review after the Tester passes. Use whenever a task needs to be turned into something the SWE can build, or whenever a task needs the final "is this actually right for users?" review before commit.
Agent
Implements a single groomed task assigned by the orchestrator. Writes code and tests locally. Does NOT commit until the Tester has reviewed and approved. Use when a task is groomed and ready for implementation, or when the Tester has returned feedback that needs to be addressed.
Agent
Reviews the software-engineer's uncommitted work against the spec and acceptance criteria. Runs the full test suite, verifies every acceptance criterion with evidence, and gives PASS or FAIL. Use after the SWE reports an implementation is done, or after the SWE applies fixes for previously-flagged issues.
Skill Claude CodeCodex
Periodic architectural sweep — reads existing ADRs, maps modules/dependencies/layering, and reports up to 10 prioritised findings shaped as refactor proposals /squid-refactor can consume directly.
Skill Claude CodeCodex
Strip redundancy from prose — docs, READMEs, code comments, docstrings — keeping behaviour identical.
Skill Claude CodeCodex
Shrink an agent harness (.agents/ skills + resources) to the minimum tokens that keep the exact same logic. Never touches resources/datasets/.
Skill Claude CodeCodex
Shrink the memory files sessions load — the root AGENTS.md plus every nested AGENTS.md / CLAUDE.md — to the minimum words that state the same rules: compress wording, delete duplicates and harness-enforced claims, merge fragments.
Skill Claude CodeCodex
Interview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.
Skill Claude CodeCodex
Run the full agent-team pipeline end-to-end for one feature whose Tasks Plan is already approved by /squid-plan, handing the human a validated, ready-to-squash-merge PR. Trigger after /squid-plan, or when the user says "/squid-implement-night".
Skill Claude CodeCodex
Implement one task — or a whole list / an approved Tasks Plan — via the inner SWE↔Tester loop, committing each task on PASS. Use when one or more GROOMED tasks are ready to build, or the user says "/squid-implement-task". To plan a feature first use /squid-plan; for the full end-to-end pipeline use…
Skill Claude CodeCodex
Turn a raw feature spec into an approved Tasks Plan — grill the spec, have the Product Architect groom draft tasks (+ optional ADR and glossary additions), then run ONE human gate that decides everything touching the repo: tasks + storage, ADR, glossary, worktree, and which build to run.
Skill Claude CodeCodex
Plan a refactor as an ordered, commit-grain Tasks Plan with structural acceptance criteria (suite green at every step, no behaviour diff) that /squid-implement-night can execute end-to-end.