joenandez

Orchestrate durable XS–XL planning after confirmed Scope, with adaptive artifacts, review, tasks, telemetry, and explicit pre-code approval. Do not use for scoping, bug diagnosis, read-only work, or execution of approved artifacts.

Orchestrate durable XS–XL planning after confirmed Scope, with adaptive artifacts, review, tasks, telemetry, and explicit pre-code approval. Do not use for scoping, bug diagnosis, read-only work, or execution of approved artifacts.

Create the smallest evidence-backed plan for confirmed Scope. Use for HOW after scope or when Plan routes here; not for scope, UX, tasks, or implementation.

Internal initializer for a missing Spectre feature root. Invoke only from a standalone workflow with no confirmed managed root. Do NOT invoke for existing roots, orchestrated calls missing a root, or direct user requests.

Correct and aggressively simplify plan.md after create_plan. Do not review tasks/code, change Scope, or add speculative completeness.

Research a codebase to answer a question — fan out read-only agents (finder/analyst/patterns, web-research for 3rd-party), then synthesize evidence-backed findings into a saved research doc with file:line citations. Use when the user asks "how does X work",…

Create the smallest evidence-backed plan for confirmed Scope. Use for HOW after scope or when Plan routes here; not for scope, UX, tasks, or implementation.

Correct and aggressively simplify plan.md after create_plan. Do not review tasks/code, change Scope, or add speculative completeness.

Use when modifying the Codex CASPAR install flow, project skill syncing, learn/recall registry files, or Codex-specific runtime files. TRIGGER when: codex, caspar, codex install, project skills, registry, caspar-learn, caspar-recall, config.toml, doctor

Run an independent adversarial code review of completed work using a pinned high-effort opposing runtime, with a same-contract native fallback. Finds bugs, correctness and security failures, regressions, performance landmines, overengineering, and missing…

Build the planned feature from a compact execute.md index and sliceable tasks.json detail, dispatching parallel task waves through deterministic checks, lightweight sentinel review, and final adversarial review/validation. Trigger after execute.md/tasks.json…

Use when rendering the Next Steps footer at the end of any caspar command, suggesting which caspar command to run next, or answering "what command should I run?" / "how does the workflow work?". Do NOT use mid-task or for executing a phase — this only renders…

Independent adversarial review of plan.md before task generation. Use a pinned high-effort opposite-runtime reviewer; fall back to one native reviewer with the same contract when unavailable. Trigger after create_plan and before create_tasks. Do NOT review…

Adversarial review of generated execute.md + tasks.json against a reviewed plan using a pinned high-effort opposite runtime, with a same-contract native fallback. Checks translation, criteria, RED pairing, dependencies, waves, and alignment. Do NOT review…

Run an independent adversarial code review of completed work using a pinned high-effort opposing runtime, with a same-contract native fallback. Finds bugs, correctness and security failures, regressions, performance landmines, overengineering, and missing…

Build the planned feature from a compact execute.md index and sliceable tasks.json detail, dispatching parallel task waves through deterministic checks, lightweight sentinel review, and final adversarial review/validation. Trigger after execute.md/tasks.json…

Use this skill when you see @name or /name patterns in user input without file identifiers. This means the user is trying to call a subagent or slash command using Spectre Agent Tools. The @ prefix dispatches to a subagent (e.g., '@tdd-agent write tests',…

Use when modifying build loop code, debugging stats/token tracking, adding CLI features, changing iteration prompts, or understanding how spectre-build works end-to-end

Use when modifying the plan loop, debugging plan stages, changing clarification flow, scope isolation, or understanding how spectre-build --plan works end-to-end

Use when modifying the ship loop, debugging ship stages, changing clean/test/rebase behavior, or understanding how spectre-build --ship works end-to-end

Use when user wants to search for existing knowledge, recall a specific learning, or discover what knowledge is available.

Use when planning product scaling, adding GUI/server layers, multi-model support, adversarial reviews, live steering, telemetry, scheduling/triggers, or node-based pipeline editors to spectre-build

Use when working with pipeline stages, completion strategies, build loop orchestration, or the web GUI for spectre-build

Use when starting implementation, debugging, or feature work on a project with captured knowledge.