ThumbGate — PreToolUse Agent Firewall

Capture an up/down signal plus one line of why. Vague feedback is logged, then returned with a clarification prompt instead of memory promotion.

Get summary of recent feedback

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

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

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

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

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

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

Get feedback stats and recommendations

No parameter schema in public metadata yet.

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

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

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

Generate an intent execution plan with policy checkpoints

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

Complete a sequential delegation handoff and record verification outcomes

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

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

No parameter schema in public metadata yet.

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

No parameter schema in public metadata yet.

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.

Capture success/failure feedback to harden future workflows. Aliased to capture_feedback.

Normalize a GitHub/Slack/Linear trigger into startup context, construct a recall pack, prepare a git worktree sandbox, and emit an execution plus reviewer-lane plan.

Generate prevention rules from repeated mistake patterns

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.

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

Construct a bounded context pack from contextfs

Record evaluation outcome for a context pack

Get recent context/provenance events

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

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.

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...

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.

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

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

No parameter schema in public metadata yet.

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

Return the active branch and release governance state.

No parameter schema in public metadata yet.

Grant a time-limited approval for edits or publish actions that touch protected files.

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

Check whether a claim has enough tracked evidence before the agent asserts it.

Evaluate whether the current repo state is safe for PR, merge, release, and publish operations.

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

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

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

No parameter schema in public metadata yet.

Get full ThumbGate dashboard -- Harness Score, gate stats, prevention impact, proof, and system health

No parameter schema in public metadata yet.

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.

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

No parameter schema in public metadata yet.

Recall past feedback filtered by commerce categories (product_recommendation, brand_compliance, sizing, pricing, regulatory). Returns quality scores alongside memories for agentic commerce agents.

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

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

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

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.

No parameter schema in public metadata yet.

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

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

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.

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

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

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

Append a follow-up message to an open feedback session. Call this when the user types additional context after giving thumbs up/down.

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

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

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

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.

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.

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

No parameter schema in public metadata yet.

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.

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

No parameter schema in public metadata yet.

Dump ALL prevention lessons into a single text block for context-window injection. Bypasses RAG/search — returns every lesson sorted by confidence. For most projects (20-200 lessons), fits in 1K-10K tokens.