Results for “adversarial-review”

Adversarial code review using parallel review layers and structured triage. Use when the user says "run code review" or "review this code"

Uses two independent review agents to verify output quality, requiring both to pass before shipping.

Performs security-focused differential review of code changes (PRs, commits, diffs), adapting analysis depth to codebase size and generating comprehensive markdown reports.

Decide whether an article deserves publication through hard checks and skeptical comparison.

Pressure-test any business idea with a five-angle adversarial panel (Critic, Champion, Analyst, Investigator, Customer) that returns a single GO/RESHAPE/KILL verdict with the cheapest test to de-risk it.

Skeptical pushback on visual placement — both density and quality. Reads the annotated outline plus the visuals manifest and asks (a) whether the article hits the density target from editorial-principles-visuals.md, (b) whether each [VISUAL:...] earns its place, (c) whether sections without one would benefit. One revision pass on FAIL (BLOG_AGENT_VISUALS_REVISION_BUDGET, default 1).

Runs independent AI CLI reviewers over phase plans and merges their feedback into a REVIEWS.md file.

Simulates a NeurIPS/SC/ICSE-style peer review with five reviewer personas (HPC, ML, Stats, Reproducibility, Devil's Advocate) that verify every claim against actual result data before submission.

Skeptical pushback on the outline before drafting starts. Asks whether the outline is MECE, BLUF, problem-agitate-solution; whether it covers the topic better than the SERP top-5; whether sections duplicate; whether each section earns its visual. One revision pass on FAIL (BLOG_AGENT_OUTLINE_REVISION_BUDGET, default 1).

Adversarially verify an implementation against its objective, acceptance criteria, definition of done, and prohibitions using fresh evidence. Use for completion gates, release readiness, or independent verification after implementation and review.

Temporarily turn off the requirement that pending changes be reviewed before committing in the current herdr workspace.

Turn interactive commit reviews back on for the current herdr workspace.

Adversarial one-question-at-a-time questioning to verify deep reading comprehension of alignment pages, specs, or any document

Multi-perspective dialectical reasoning with cross-evaluative synthesis. Spawns parallel evaluative lenses (STRUCTURAL, EVIDENTIAL, SCOPE, ADVERSARIAL, PRAGMATIC) that critique thesis AND critique each other's critiques, producing N-squared evaluation matrix before recursive aggregation. Triggers on /critique, /dialectic, /crosseval, requests for thorough analysis, stress-testing arguments, or finding weaknesses. Implements Hegelian refinement enhanced with interleaved multi-domain evaluation and convergent synthesis.

Incident Post-Mortem Builder

Reviewer Role Session

Convene a four-voice council of advisors to surface structured disagreement and tradeoffs for ambiguous decisions, go/no-go calls, and multi-path choices.

Generate a step-by-step construction plan from a one-line objective, with dependency graphs, parallel step detection, and adversarial review for multi-session engineering projects.

Orchestrate autonomous AI development pipelines through your Kanban board, managing multi-worker Claude Code dispatch, deterministic quality gates, adversarial review, per-task cost tracking, and crash-proof pipeline execution.

OpenAI Codex CLI wrapper — three modes. Code review: independent diff review via codex review with pass/fail gate. Challenge: adversarial mode that tries to break your code. Consult: ask codex anything with session continuity for follow-ups. The "200 IQ autistic developer" second opinion. Use when asked to "codex review", "codex challenge", "ask codex", "second opinion", or "consult codex". (gstack) Voice triggers (speech-to-text aliases): "code x", "code ex", "get another opinion".

Delivers a small, bounded code change through inspection, a mini-plan, implementation, testing, review, and adversarial verification. Use for bug fixes, configuration changes, and features expected to touch no more than five files.

Score an unbuilt business idea on desirability, viability, feasibility, distribution wedge, why-now, founder-market-fit, market size, alternatives, defensibility, capital intensity, and regulatory/ethical risk — and return a GO / ITERATE / KILL verdict with kill criteria and a next kill test. Load when the user asks to evaluate a business idea, score a startup idea, screen an idea, decide whether to pursue this venture, do an idea review, or says "is this a good business idea", "should I build this", "evaluate this startup", "screen this idea", "go/no-go on this idea", "kill or pursue". Sub-skill of `venture-exploration`. Calls `fermi` for sizing, `assumption-mapping` for hidden beliefs, optional `pre-mortem` / `adversarial-hat` for high-stakes ideas. Does NOT evaluate built products — for that use `reality-check`.