Skill Claude CodeCodex
Manual-only orchestration of GitHub issues in dedicated Herdr work units: triage, delegate, scope-check, ship, merge, and dismantle. The user owns blocked decisions and holds for high-risk or visible UI work.
Skill Claude CodeCodex
Manual-only orchestration of GitHub issues in dedicated Herdr work units: triage, delegate, scope-check, ship, merge, and dismantle. The user owns blocked decisions and holds for high-risk or visible UI work.
Skill Claude CodeCodex
Persistent Claude-Codex pairing inside one Herdr tab. Use for live peer work, workflows requesting a pair, or any inbound [agent ...] / [herdr-pair control ...] line — including after context compaction; resume the exact session and reply through the bundled transport.
Skill Claude CodeCodex
Manual-only visual exploration before implementation. Invoke explicitly to explore and choose interface, product, campaign, or brand directions using imagegen, optional brandkit proof, and one-question-at-a-time intake.
Skill Claude CodeCodex
Ask the opposite model for one focused opinion, review, or scoped pass without a live Herdr pair. Codex may consult Fable autonomously; Claude Code consults Codex only when explicitly invoked.
Skill Claude CodeCodex
Read-only audit of this machine against a named CVE, malicious package, or supply-chain advisory. Use only when explicitly asked whether this machine is affected; not for general security review, news, breach response, or remediation.
Skill Claude CodeCodex
Evidence-driven debugging for unresolved, flaky, environment-specific, or production-only bugs. Use when asked to diagnose or when normal inspection cannot prove the cause; skip obvious errors and already-proven causes.
Skill Claude CodeCodex
Draft or edit Henrique's writing in his voice, or flag concrete AI-slop patterns without rewriting. Use for English or European Portuguese.
Skill Claude CodeCodex
Manual-only orchestration of an explicit task list through isolated worktrees, persistent pairs, pull requests, verified merges, and cleanup.
Skill Claude CodeCodex
Persistent two-agent pairing across claude, codex, cursor, grok, and opencode, in a Herdr tab or headless outside it. Use for live peer work, workflows requesting a pair, any inbound [agent ...] / [herdr-pair control ...] line, resuming a pair after context compaction, or pairing with another CLI when Herdr is absent.
Skill Claude CodeCodex
Manual-only graded review gate for a finished change: risk grade, one simplify pass, one graded LLM review round, one material correction batch, then a receipt. Leaves a clean local HEAD and never pushes, opens, or merges anything. Invoke only when the user explicitly names review-it or an explicitly invoked workflow…
Skill Claude CodeCodex
Manual-only cleanup of actual feedback on an existing PR: verify comments, batch valid in-scope fixes, respond, and leave the PR merge-ready.
Skill Claude CodeCodex
Manual-only delivery for finished work: focused proof, the graded review gate, deterministic final-HEAD validation, then push, PR, CI, and authorized merge. Invoke only when the user explicitly names ship-it or another explicitly invoked workflow delegates its delivery.