fh-meta

Frontier-grade first-contact standpoint evaluator. Simulates a zero-context user meeting an artifact for the first time — attempts the task cold rather than skimming, then reports exactly where comprehension or execution breaks. Lowest tier of the user-mastery spectrum (beginner → main-player → expert). Constructive standpoint, not an adversary — surfaces onboarding friction a fluent author cannot feel. Returns parallax-compatible [Strengths / Concerns / Absence check / Open questions]. Use when you need a true cold-read of a SKILL, README, prompt, or onboarding path.

Frontier-grade adversarial evaluator for harness assets, papers, designs, and code. Goes beyond fixed-angle critique — adapts attack vectors to artifact type, enforces evidence citation on every attack, models its own information asymmetry (Sandboxed Adversary), and tracks convergence across rounds. Returns structured [issue · location · severity] output consumable by steel-quench, harvest-loop, and sim-conductor. Use when you need adversarial pressure that a self-reviewing author cannot generate.

Frontier-grade domain-authority evaluator. Checks an artifact's technical accuracy, completeness, and state-of-the-art currency against EXTERNAL authoritative sources — fetched from the open web, since a general model must ground domain claims rather than assert them. Top tier of the user-mastery spectrum (beginner → main-player → expert): the professor / prolific author / frontier-harness operator. Every accuracy judgment carries an external citation; ungrounded assertions are withheld. Returns parallax-compatible output. Use when "is this technically correct and current with the field?" matters.

Use when (1) about to recommend an asset, skill, or agent that may already exist in the hub, (2) memory or docs contain stale facts, dates, or references, or (3) duplicate work is suspected. Greps hub assets and reports findings. Not for general code review or external persona audits.

Use when an external-facing draft (briefing, card, guide) is ready for pre-publication audit. Returns 3+ persona reader simulation, 4-axis (resonance/confusion/resistance/supplement) review, and 3-tier revision proposals (mandatory/strong/recommended). Do not use for internal memos, CATALOG entries, memory files, code review, or PR review.

Given a task description, searches internal and external open-source ecosystems (including Codex marketplace and Claude Code marketplace) to find and recommend suitable plugins with installation guidance. Recommendation is quality-validation based (marketplace-listed + performance-validated), not source-origin based. Activates on "recommend a plugin", "what tool should I use?", "is there a plugin for this?", "recommend a tool". Also checks for duplicate installations.

Detects harness regressions by running standard prompt probes after rule/skill changes and comparing outputs against saved baselines. Triggers on "prompt regression", "did my changes break anything", "regression check", "test harness changes".

Scans git-tracked (public) files for operator-private tokens that should live only in gitignored files — real usernames, absolute home paths, companion-store names, company asset names. Reports file:line + matched token + severity, so a public/private split stays clean before publish. Triggered by "public surface audit", "did I leak anything", "check tracked files for private tokens", "private token scan", "public-surface-audit".

Audits SKILL.md files in plugins/ for return-path gate compliance. Detects fire-and-forget chains where a caller dispatches a downstream skill but does not gate its next step on the callee's verdict. Reports each chain as CLOSED or OPEN and outputs specific fix suggestions. Triggered by "chain audit", "return-path check", "fire-and-forget detection", "chain closure audit", "skill chain compliance".

DEPRECATED — merged into harness-doctor --lint mode (2026-06-02). Language pattern detection (self-marketing, cushion words, version labels) is now Step 3-L of harness-doctor. Use /harness-doctor --lint instead.