thumbgate

skool-headless-reader

Read, monitor, and analyze Skool communities or posts headlessly for lead discovery, customer pain, acquisition opportunities, or ThumbGate revenue research without blocking the user's browser.

Triage a CI / PR check failure by READING the failure body before forming any hypothesis. Triggered whenever a required check is red, a PR is BLOCKED, a merge won't land, or you're about to call a failure "transient", "flaky", "stale", or "orphaned". Prevents dismissing a real failure (e.g. real CodeQL security alerts) as noise.

evidence-first-answer

Required pre-flight before answering any "why" or "are we" question about revenue, conversion, outbound, traffic, or commercial state. Forces verification of live data and distinguishes planning docs from telemetry. Triggered automatically when the CEO asks "are you sure?" — that phrase means the previous answer was wrong.

revenue-truth

Fetch live ThumbGate revenue, paid orders, and funnel telemetry from production billing endpoints. Use BEFORE answering any question about money, conversion, traffic, or "why we didn't make X." Never quote planning documents as actuals.

scope-discipline

Keep one task closed-looped before starting the next. Triggered when a new problem surfaces mid-task (a bug, a security finding, a missing env var), when you're about to branch into unrelated work, or when you notice the session has sprawled across many half-finished threads. Prevents the "nothing ever lands" failure where each step spawns new work and none finishes.

task-state-ledger

Maintain an external state ledger for any multi-step task (3+ steps, multi-PR, anything spanning more than one turn or touching production). Triggered when you notice yourself re-deriving "where am I" with repeated gh/git/curl dumps, when a task crosses turns, or when the user asks "why are you stuck/lost". Prevents the "lost" failure mode: re-discovering state every turn instead of reading it.

thumbgate-feedback

Capture thumbs feedback and apply prevention rules before coding

Code & Development Listed

adversarial-review

Run a skeptical Codex review from Claude Code that hunts for hidden regressions, unsafe assumptions, and release risk. Use before merges, deploys, migrations, or other risky changes.

result

Print the latest saved Codex bridge result from Claude Code without rerunning Codex. Use when the user asks for the last Codex output or wants to inspect the raw bridge result.

Code & Development Listed

review

Run a Codex review from Claude Code against the current uncommitted work, a base branch diff, or a specific commit. Use when the user explicitly asks for a Codex review or second reviewer.

second-pass

Hand the current task or repo state to Codex for an independent second pass from inside Claude Code. Use when the user explicitly wants another agent to take a shot after Claude's first pass.

setup

Validate that the Codex bridge plugin is ready inside Claude Code. Use when the user asks to install, configure, or sanity-check Codex review from Claude.

Show all 26 bundled skills

capture-feedback

Capture structured thumbs up/down feedback with context, history-aware lesson distillation, tags, and optional rubric scores after completing a task.

prevention-rules

Generate and review prevention rules auto-promoted from repeated failure patterns.

programmatic-agent-runs

Govern Cursor SDK local, cloud, self-hosted, and subagent coding runs before they create branches or PRs.

recall-context

Recall relevant past failures, prevention rules, and context packs before starting a coding task.

search-lessons

Search promoted lessons for corrective actions, lifecycle state, linked rules, and linked gates.

agent-memory

Give your agent persistent cross-session memory — recall what went wrong on similar tasks before starting, then capture whether the work succeeded or failed so repeated mistakes auto-promote into prevention rules. Runs locally via the ThumbGate MCP server (recall, capture_feedback, prevention_rules, feedback_stats) — no API key needed. Use when the user says "recall", "what went wrong last time", "remember this for next time", "capture feedback", "thumbs up/down on that", or at the start of a new task or session. Do NOT use when the user wants to force one specific mistake into an enforced block gate (use the thumbgate-guard skill), to list rules that already exist (thumbgate-rules), or to check ThumbGate wiring (thumbgate-doctor).

bluesky-engagement

Automated Bluesky reply monitoring and draft queueing for ThumbGate's acquisition engagement loop. Polls the AT Protocol notifications endpoint every 15 minutes, writes human-reviewable draft replies into a queue file, and never auto-posts without sign-off. Trigger when the user asks about Bluesky replies, engagement, reply monitoring, or wants to see/approve queued drafts. Also the authoritative reference for rotating the Bluesky app password or diagnosing monitor failures.

solve-architecture-autonomy

Course-correct from over-planning to execution — when the agent has produced a plan, research, or options instead of doing work the user already approved, drop the analysis and execute the smallest end-to-end action now (branch, run, deploy, verify). Use when the user says "stop planning, just do it", "why are you researching, execute", "just ship it", "enough analysis", or pushes back that you keep proposing instead of acting on an already-decided task. Do NOT use when the task is genuinely undecided and needs a plan first, when the user explicitly asked for research/options/a design, or for routine work where no over-planning has occurred — acting on an unscoped or destructive task is its own failure.

thumbgate-blocked

Show ThumbGate's enforcement record — how many risky actions were actually blocked versus warned, which gates fire most, the tokens/damage saved, and the full feedback to check to rejection pipeline. Reads live enforcement counters via the gate_stats and enforcement_matrix MCP tools (CLI fallback `npx thumbgate gate-stats`). Use when the user says "what has ThumbGate blocked", "show gate stats", "is enforcement working", "how many tokens did we save", "show the enforcement matrix", or "what got stopped". Do NOT use to list rule DEFINITIONS that exist (use the thumbgate-rules skill), to create a new rule (use the thumbgate-guard skill), or to check whether ThumbGate is installed and wired (use the thumbgate-doctor skill).

thumbgate-doctor

Health-check whether ThumbGate is actually wired into this agent — PreToolUse/SessionStart hooks installed, MCP server reachable, lesson store present, statusline, and overall agent-readiness — then report exactly what to fix. Runs the existing `npx thumbgate doctor` audit and the check_operational_integrity MCP tool. Use when the user says "is ThumbGate wired up", "thumbgate doctor", "check my guardrails are installed", "why aren't my gates firing", "is the MCP server connected", or "agent readiness". Do NOT use to view rules (use the thumbgate-rules skill), to view what was blocked (use the thumbgate-blocked skill), or to capture a new rule (use the thumbgate-guard skill) — this skill only diagnoses setup and wiring.

thumbgate-guard

Turn the agent's most recent mistake into an enforced ThumbGate prevention rule (a PreToolUse block gate) so the same bad tool call is intercepted before it runs again, in this and every future session across Claude Code, Cursor, Codex, Gemini, Amp, and Cline. Captures the failure with the capture_feedback MCP tool, then force-promotes it via `npx thumbgate force-gate` so it is enforced, not just logged. Use when the user says "guard against this", "block this from happening again", "never do that again", "make that a rule", "stop the agent from repeating that", or right after a bad action or thumbs-down that should become a hard rule. Do NOT use to merely log a thumbs-up/down without enforcement (use the thumbgate-feedback skill), to recall prior context before starting work (use the Agent Memory skill), or to list rules that already exist (use the thumbgate-rules skill).

thumbgate-protect

Inspect this repo's branch and release governance (protected branches, release rules, protected-file globs) and, only when the user explicitly approves, grant a scoped, time-limited exception so a protected-file edit or publish can proceed under audit. Reads posture via the get_branch_governance MCP tool and records a narrow, expiring approval via the approve_protected_action MCP tool. Use when the user says "is main protected", "show branch governance", "what am I blocked from editing", "approve this protected change", or "let me edit a protected file just this once". Do NOT use to disable protection wholesale, to grant broad or standing exceptions, or to diagnose hook wiring (use the thumbgate-doctor skill) — this skill is for narrow, temporary, audited approvals only.

thumbgate-rules

List the active ThumbGate prevention rules, reliability rules, and the promoted lessons behind them, so the user can see which guardrails are currently protecting this project and WHY each one exists. Reads the live rule and lesson stores via the prevention_rules, get_reliability_rules, and search_lessons MCP tools (CLI fallback `npx thumbgate rules`). Use when the user says "what is ThumbGate protecting me from", "show my rules", "show my gates", "what has the agent learned", "list active guardrails", or "what's blocked here". Do NOT use to CREATE a new rule (use the thumbgate-guard skill), to see runtime enforcement counts of what actually fired (use the thumbgate-blocked skill), or to diagnose whether ThumbGate is wired up at all (use the thumbgate-doctor skill).

thumbgate

ThumbGate provides pre-action gates for AI coding agents. It captures thumbs-up/down feedback on agent actions, auto-promotes repeated failures into prevention rules, and blocks known-bad tool calls via PreToolUse hooks. Trigger when the user wants to add safety guardrails to an AI agent workflow, capture structured feedback on agent output, generate prevention rules from failure patterns, gate high-risk actions before execution, or export DPO training pairs from production feedback. Works with any MCP-compatible agent including Cursor, Codex, Gemini CLI, Amp, and OpenCode.