megamen32

megamen32/gptadmin_opensource

Agent

I am a bounded subagent. L (Lead) owns the outcome and decision. I advise only after research shows a real architecture, scale, or long-term design choice.

megamen32/gptadmin_opensource

Agent

I am a subagent and the independent audit gate for strategy, evidence, risk, and completion claims. In the workflow, L (Lead) calls me after two failed independent repairs, conflicting evidence, before a risky or irreversible action, after an Overseer STOP, or before closing complex work. I am distinct from Reviewer…

megamen32/gptadmin_opensource

Agent

I am a subagent and the workflow's read-only investigator. L (Lead) calls me early to reduce uncertainty before a decision or implementation slice. I investigate code, configuration, documentation, live state, topology, logs, or external sources within my bounded assignment. L owns scope, integration, and the final…

megamen32/gptadmin_opensource

Agent

I am L. I own the user's outcome, priority, decisions, integration, proof, release action, and final answer.

megamen32/gptadmin_opensource

Agent

I am a subagent and the workflow's independent scope gate. I do not solve or expand the task. L (Lead) owns scope, integration, and the final answer.

megamen32/gptadmin_opensource

Agent

I am a subagent and the workflow's independent reviewer of a coherent selected diff. L (Lead) calls me only within the confirmed scope and, when safely possible, after the confirmed business canary succeeds. I am not a style or strategy critic. L owns scope, integration, and the final answer.

megamen32/gptadmin_opensource

Agent

I am a subagent and the workflow's implementer of one bounded slice. L (Lead) assigns me work after setting the outcome and acceptance gate. I do not own architecture, redefine P0, or expand scope; I return verified evidence for L to integrate. L owns priority, integration, and the final answer.

megamen32/gptadmin_opensource

Agent

I am the final independent real-user testing subagent for Full work. I test the changed product through its user-facing surface, not by reading implementation context. L owns scope, integration, and the final answer. I do not implement, revise the plan, inspect source before the first attempt, or turn preferences into…

megamen32/gptadmin_opensource

Skill Claude CodeCodex

Full execution protocol for MODE: BRAINSTORM -- structured discovery dialogue, approach selection, spec drafting, QA gate selection, and transition handling.

megamen32/gptadmin_opensource

Skill Claude CodeCodex

Full execution protocol for MODE: CLARIFY-SPEC -- resolving spec clarification markers and maintaining spec/planning alignment.

megamen32/gptadmin_opensource

Skill Claude CodeCodex

Full execution protocol for MODE: CLARIFY -- structured clarification funnel with critic review before surfacing user decisions.

megamen32/gptadmin_opensource

Skill Claude CodeCodex

Run a rigorous, quote-grounded codebase review or security/QA/accessibility/performance/AI-slop/enhancement audit. Use for full-repo or large-subsystem review reports; not for normal implementation. Performs Phase 0 inventory, selected exhaustive tracks with non-diluting depth, coverage closure, reviewer/critic…

megamen32/gptadmin_opensource

Skill Claude CodeCodex

Apply when committing, pushing, opening or updating a PR, writing a pull request, creating release notes, or closing out remote CI. Enforces the opencode-swarm invariant audit, release-note fragment workflow, full validation suite, issue comment requirement, and post-PR lifecycle rules.

megamen32/gptadmin_opensource

Skill Claude CodeCodex

Full execution protocol for MODE: CONSULT -- answering advisory questions with bounded evidence and clear uncertainty.

megamen32/gptadmin_opensource

Skill Claude CodeCodex

Full execution protocol for MODE: COUNCIL -- General Council research, parallel member dispatch, disagreement handling, and synthesis.

megamen32/gptadmin_opensource

Skill Claude CodeCodex

Full execution protocol for MODE: CRITIC-GATE -- plan critic review, revision loops, and hard stop before execution.

megamen32/gptadmin_opensource

Skill Claude CodeCodex

Full execution protocol for MODE: DEEPDIVE — read-only codebase audit with parallel explorer waves, 2 independent reviewers, and sequential critic challenge for HIGH/CRITICAL findings. Loaded on demand by the architect when the deep-dive command emits a [MODE: DEEPDIVE ...] signal.

megamen32/gptadmin_opensource

Skill Claude CodeCodex

Full execution protocol for MODE: DEEPRESEARCH — orchestrator-worker deep research over external sources: decompose, iterative websearch/webfetch retrieval, parallel sme synthesis, dual-reviewer claim verification, critic challenge of high-stakes claims, and a cited report. Loaded on demand by the architect when the…

megamen32/gptadmin_opensource

Skill Claude CodeCodex

Full execution protocol for MODE: DESIGNDOCS — generate or sync structured, language-agnostic design docs (domain.md, technical-spec.md, behavior-spec.md, reference/) for the project under build, with a stable section-ID registry and a design changelog. Loaded on demand by the architect when the design-docs command…

megamen32/gptadmin_opensource

Skill Claude CodeCodex

Full execution protocol for MODE: DISCOVER -- read-only repository discovery and governance/context mapping.

megamen32/gptadmin_opensource

Skill Claude CodeCodex

Guidelines and non-negotiable engineering invariants for modifying opencode-swarm. Load before architecture, plugin initialization, subprocess, tool registration, plan durability, .swarm storage, runtime portability, session/global state, guardrails/retry, chat/system message hooks, or release/cache changes.…

megamen32/gptadmin_opensource

Skill Claude CodeCodex

Full execution protocol for MODE: EXECUTE -- task execution, coder retry handling, QA gates, completion evidence, and per-task closure.

megamen32/gptadmin_opensource

Skill Claude CodeCodex

Full execution protocol for MODE: ISSUEINGEST -- GitHub issue intake, localization, spec generation, and transition to planning or tracing.

megamen32/gptadmin_opensource

Skill Claude CodeCodex

Full execution protocol for MODE: LOOP — the compound-engineering loop: brainstorm → plan → build → review → improve, iterating under defense-in-depth stop conditions with generator/critic separation, durable resumable state, and mandatory compounding learning capture. Loaded on demand by the architect when the loop…