ThumbGate

Get the canonical definition and state of a business entity (Customer, Revenue, Funnel).

Detect whether a tool call was a no-op (state unchanged) or identical to a prior attempt in the session — a cheap repeat-loop signal. Records the action attempt state for repeat detection.

Diagnose a failed or suspect workflow step using MCP schema, workflow, gate, and approval constraints.

Leader-Agent swarm coordinator. Constructs one context pack and distributes it to N worker agents (perplexity-bug-resolver, codex-reviewer, grok-x-intelligence, etc.), recording provenance per agent. Replaces N independent context derivations with a single shared pack.

Show the full Enforcement Matrix: feedback pipeline stats, active pre-action checks, and rejection ledger with revival conditions.

Estimate Bayesian uncertainty for a set of tags based on past feedback.

Record evaluation outcome for a context pack

Run shell commands

Export ThumbGate logs and proof artifacts as a Databricks-ready analytics bundle

Export DPO preference pairs from local memory log

Export ThumbGate agent traces and DPO preference pairs as a HuggingFace-compatible dataset. Produces traces.jsonl, preferences.jsonl, and dataset_info.json with PII-redacted paths. Ready for huggingface-cli upload.

Get feedback stats and recommendations

Get summary of recent feedback

Finalize a feedback session and re-infer the lesson with all follow-up context.

Returns follower count snapshots for a platform over the past N days.

Evaluate a proposed tool call against ThumbGate policy BEFORE executing it. Returns decision "block" (do not run the action; surface the reason) or "allow". Use this when about to run a shell command, write/edit a file, or take any irreversible action.

Get gate enforcement statistics -- blocked count, warned count, top gates

Dynamic operator artifact generator. Turns ThumbGate PR, reliability, revenue, and release data into a decision-ready pulse with metrics, evidence, and next actions.

Auto-generate Claude skills from repeated feedback patterns. Clusters failure patterns by tags and produces SKILL.md files with DO/INSTEAD rules.

Read outcome-paired action receipts. Returns the receipt for a specific actionId, or the most recent receipts when no actionId is given.

Compute transparent task, tool, safety, escalation, latency, cost, and business metrics from recorded task outcomes. Empty data returns insufficient_evidence.

Return the active branch and release governance state.

Read recent broker-signed execution receipts from the local ledger.

Retrieve high-level business metrics (Revenue, Conversion, Customers) from the Semantic Layer.

Read a previously imported document with its proposed gate candidates and provenance.

Retrieve active prevention rules and success patterns. Aliased to prevention_rules.

Return the active task scope and any unexpired protected-file approvals.

Read a task outcome by taskId or the most recent evidence-backed outcome receipts.

Import a local policy or runbook document into ThumbGate, normalize it for search, and propose provenance-backed gate candidates.

Perform autonomous inference on chat history to identify why a failure occurred and what rule should be recorded.

Not available on the agent MCP surface. Brokers issue receipts out-of-band via scripts/broker-execution-receipts.js with THUMBGATE_BROKER_SIGNING_KEY.

List natural-language harness specs for portable workflow control, proof-backed verification, and GTM execution.

List auditable human-escalation state. Approval decisions are deliberately absent from the agent tool surface.

List imported policy and runbook documents stored in local ThumbGate state.

List available intent plans and whether each requires human approval in the active profile

List projected purchase-requisition states from the append-only financial ledger and human-review queue.

Show status of the last managed lesson agent run: entries processed, lessons created, gates promoted, and total runs.

Audit local browser native messaging hosts and AI browser bridges. Flags missing host binaries, pre-authorized extension bridges, and manifests for browsers not detected locally.

Open a feedback session after thumbs up/down. Follow-up messages will be captured for 60s.

Org-wide multi-agent dashboard — shows all active agents, gate decisions, adherence rates, risk agents, and top blocked gates across the organization. Team rollout: full visibility. Free preview: limited to 3 agents.

Execute a parallel, multi-step subtask workflow to resolve an objective like a security audit, performance benchmark, or repository inspection.

Evaluate an agent workflow before adding tools, autonomy, or subagents. Recommends single-agent vs manager/decentralized patterns, baseline evals, instruction fixes, and tool safeguards.

Prepare ThumbGate intent clusters, ad copy, proof links, UTM measurement, and launch gates for ChatGPT Ads Manager tests.

Estimate MCP schema and feedback-context footprint before loading large manifests into an agent prompt. Reports progressive-discovery savings, context compaction savings, and proof-preserving recommendations.

Generate an intent execution plan with policy checkpoints

Plan a high-ROI multimodal retrieval rollout for screenshots, PDF pages, dashboard captures, and proof artifacts without starting GPU training.

Rank upstream GitHub repositories ThumbGate depends on for proof-backed issue, bounty, and PR opportunities without spammy drive-by contributions.

Map proactive-assistant eval gaps to PARE-style state-machine, active-user-simulation, goal-inference, intervention-timing, and multi-app orchestration gates.

Detect reward-hacking patterns such as unsupported completion claims, sycophancy, verbosity-as-proof, benchmark overfitting, evaluator manipulation, and proxy-only metrics.

Generate prevention rules from repeated mistake patterns

Returns aggregated engagement metrics from the social analytics database for the given platform and time window.

Recall relevant past feedback, memories, and prevention rules for the current task. Call this at the start of any task to inject past learnings into the conversation.

Verify signatures and hash-chain continuity for all broker execution receipts on the ledger.

Reconcile the append-only financial ledger, including totals, stale reservations, status counts, and tamper-evident event hashes.

Pair a tracked tool call with its outcome (diff, exit code, test result) so a promoted lesson encodes "this action -> this outcome", not just a thumbs signal. Appends to the action-receipts log.

Append a verified broker-signed execution receipt to the local hash-chained ledger.

Record an idempotent task-level outcome with verification evidence, tool correctness, policy behavior, latency, cost, and business KPI movement. A completed response without evidence is recorded as not working.

Run a post-mortem analysis on negative feedback. Returns a proposed rule and recurrence info.

Register a custom claim verification rule in local runtime state without editing tracked repo config.

Report a bug, suggestion, or complaint about ThumbGate itself (not project feedback). Auto-files a GitHub issue with system context. Use when the user expresses frustration or requests a feature for the thumbgate tool.

Create an idempotent, expiring human-review request with requester identity and evidence. Agents cannot approve their own requests.

Leader-Agent completion gate. Before any agent declares done/fixed/shipped/resolved, require tracked session evidence AND recheck parseable factual claims (row counts, file metrics, versions) against configured verifiers. Blocking response when evidence is missing or a factual claim mismatches; callers honor the blocking flag to stop completion claims.

Reserve a single-use amount from an independently approved purchase requisition. Approval is unavailable from the agent tool surface.

Retrieve the most relevant lessons for a given tool/action context. Use in PreToolUse hooks for per-action guidance.

Run a bounded metric-improvement loop: measure a baseline, test a hypothesis, require primary and holdout checks, then keep or discard the candidate mutation with proof.

Execute a natural-language harness through the async job runner with checkpoints, verification, and proof-backed outcomes.

Run the LLM-powered lesson inference and rule generation agent over accumulated feedback. Requires ANTHROPIC_API_KEY for LLM mode; falls back to heuristics if unavailable.

Run the self-distillation agent to auto-evaluate recent agent sessions and generate improvement lessons without human feedback. Reads conversation logs, detects success/failure signals, and persists lessons.

Satisfy a gate condition with optional structured reasoning. Evidence is stored with a 5-minute TTL. When structuredReasoning is provided, the premise/evidence/conclusion chain is stored in the audit trail.

Create, list, or delete scheduled tasks. Supports natural language scheduling like "daily 9:00", "weekly monday 8:30", "hourly". Installs as macOS LaunchAgent or Linux crontab.

Search promoted lessons and show the corrective actions, lifecycle state, prevention rules, gates, and next harness fixes linked to each result.

Search raw ThumbGate state across feedback logs, ContextFS memory, prevention rules, and imported policy documents.

Scan code for OWASP vulnerabilities (injection, XSS, path traversal, SSRF, prototype pollution) and supply chain risks (typosquatting, install script abuse, wildcard versions). Returns findings with severity, category, and line numbers.

Show status of the last self-distillation run: sessions analyzed, lessons generated, signals detected.

Write a session handoff primer that auto-captures git state (branch, last 5 commits, modified files), last completed task, next step, and blockers. The next session reads this automatically for seamless context continuity.

Read the most recent session handoff primer to restore context from the previous session. Call at session start.

Unified observability rollup. Aggregates feedback stats, gate stats, and recent context/provenance events over a time window in one call. Replaces separate dashboard/gate_stats/feedback_stats calls with a single LangSmith-style report.

Search past session notes and conversations using full-text search. Returns relevant sessions from the SQLite FTS5 index for cross-session recall.

Declare or clear branch and release governance so PR, merge, release, and publish actions can be evaluated against explicit workflow state.

Declare or clear the current task scope so ThumbGate can compare affected files and diffs against the approved path set.

Resolve managed, user, project, and local ThumbGate settings with per-field origin metadata for policy visibility.

Commit actual spend with receipt evidence or release an unused reservation. Events are append-only.

Read a single Skool post URL headlessly and return normalized post metadata and content when available. Read-only.

Read a Skool community page headlessly and return normalized categories, posts, and engagement metadata. Read-only.

Rank Skool posts for ThumbGate acquisition opportunities, pain points, and high-intent outreach angles. Read-only.

Returns a full digest object summarising all social metrics, follower deltas, and top content for the past N days.

Start a sequential delegation handoff from a delegation-eligible intent plan

Suggest corrective actions for a described failure by searching the lesson DB and prevention rules. Returns up to 3 ranked suggestions with their source. Call this when something goes wrong and you need guidance on what to do next.

Read-only pointer to ThumbGate plans. Does not start any purchase; buying always requires a human on the pricing page.

What ThumbGate is: an infrastructure firewall for AI coding agents. Captures feedback, promotes it to memory, generates prevention rules, and blocks known-bad tool calls via PreToolUse hooks. Returns the install command and key links.

Read-only live health of the hosted ThumbGate service: status, version, build.

Returns top content items ranked by total engagement (likes + comments + shares + saves) over the past N days.

Record a verification action in the current session (for example figma_verified or tests_passed). Session actions expire after one hour.

Assemble a complete, role-aware context object in one call. Combines session state, user profile, relevant lessons, prevention guards, context pack, and code-graph impact — with tiered graceful degradation (full → warm → cold). Replaces multiple recall/retrieve/session_primer calls with a single orchestrated request.

Manage persistent user profile — preferences, style, domain knowledge that persists across sessions. Actions: add, remove, replace, view.

Verify a broker-signed execution receipt (Ed25519). Rejects agent-minted or rewritten "proof". ThumbGate verifies; the broker holds provider credentials and signs.

Check whether a claim has enough tracked evidence and, for parseable factual claims (row counts, file lines/bytes/existence, versions), recheck configured SQLite/filesystem/JSON verifiers before the agent asserts it.

Send a message to Teams, Slack, or Discord via webhook. Use for status reports, alerts, and notifications.

Predict pre-action workflow risk, blast radius, and remediations before a tool call executes.