Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Kastalien-Research/thoughtbox --skill hub-auditgit clone --depth 1 https://github.com/Kastalien-Research/thoughtboxWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kastalien-research/thoughtbox/hub-audit)<a href="https://agentmods.dev/skills/kastalien-research/thoughtbox/hub-audit"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/hub-audit.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 277 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
- high Agent Snooping · line 327 Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00047 | $0.04261 |
| Opus 5 | $0.00023 | $0.02131 |
| Sonnet 5 | $0.00009 | $0.00852 |
| Haiku 4.5 | $0.00005 | $0.00426 |
Grade A, and why
hub-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 379 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hub-Based Agent-Native Architecture Audit
Orchestrate a multi-agent audit of the codebase against 8 agent-native architecture principles, coordinated through Thoughtbox Hub.
Usage
/hub-audit # Full audit (all 8 principles)
/hub-audit <principle> # Single principle deep-dive
Single principle arguments: action-parity, tools, context, shared-workspace, crud, ui, discovery, prompt-native
Hub Surface
The hub is exposed as tb.hub.* inside the thoughtbox_execute MCP tool (the only registered Thoughtbox MCP tools are thoughtbox_search, thoughtbox_execute, and thoughtbox_peer_notebook). Register once per MCP session — the returned agentId is implicit for every later hub call in that session, and coordinator role is bound to the registering agentId. Submit at most ONE state-mutating hub call per thoughtbox_execute invocation; read-only calls (tb.hub.whoami, tb.hub.readChannel, tb.hub.workspaceDigest, tb.hub.listProposals) may be freely chained.
Architecture
4 agents collaborate through a shared Hub workspace:
| Agent | Profile | Principles | Investigation Surface |
|---|---|---|---|
| Auditor-A | RESEARCHER | P1 Action Parity, P2 Tools as Primitives, P5 CRUD Completeness | Tool/API surface: tool definitions, route handlers, MCP schemas |
| Auditor-B | RESEARCHER | P3 Context Injection, P4 Shared Workspace, P8 Prompt-Native Features | Information flow: system prompts, data access, feature definitions |
| Auditor-C | RESEARCHER | P6 UI Integration, P7 Capability Discovery | User-facing: agent visibility in UI, discoverability |
| Synthesizer | REVIEWER | P9 Final Report | Reviews all proposals, calibrates scores, compiles report |
Sequential spawning (required per hub-collab findings) with 90-second verification gates.
Structured Message Protocol
All tb.hub.postMessage content MUST use one of these typed prefixes. This is the coordination backbone.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 379 lines · 47 tokens per session scan A 9f25a1fa79e2
hub-audit is a skill published in the GitHub repository Kastalien-Research/thoughtbox (64 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 4,261 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
continual-learning
Nightly refinement of an existing per-repo review-style prompt using this reviewer's own finding outcomes. Read confirmed (resolved-by-commit / thumbs-up) and dismissed (thumbs-down) findings, promote the bug patterns the team actually fixes, demote the false-positive patterns, reconcile against the current prompt…
remarc
Manage Remarc session comments and contextual feedback. Use when the user mentions Remarc sessions, comments, handoff, triage, review, addressing, resolving, status updates, or summaries.
code-review
Review ServiceNow server-side scripts for ES5 violations, ACL/injection/XSS issues, N+1 queries, missing setLimit/error handling, hard-coded sysids, and business-rule recursion risks.
pr-self-review
Draft short, plainspoken notes in the author's voice that help reviewers understand non-obvious choices, boundaries, and preserved behavior in the author's own pull request or local diff. Use when the user asks to self-review, annotate, or add reviewer context to their PR or changes. Draft locally when no PR exists…
mcp-review
Review MCP server specifications and updates for compliance, security, and quality. Use when evaluating server.json files, PRs adding/updating servers, or assessing MCP server changes. NOT for creating new entries (use add-mcp-server instead).
challenge
Use before a root-cause, done/verified claim, irreversible action, or 2nd-time fix reaches the owner (APEX or plain conversation); also fires at every eLicit/Verify gate. Not for code correctness (use sniper).