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 TheMind-AI/fluid-db --skill fluiddb-feedbackgit clone --depth 1 https://github.com/TheMind-AI/fluid-dbWrote 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/themind-ai/fluid-db/fluiddb-feedback)<a href="https://agentmods.dev/skills/themind-ai/fluid-db/fluiddb-feedback"><img src="https://agentmods.dev/badge/skills/themind-ai/fluid-db/fluiddb-feedback/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/themind-ai/fluid-db/fluiddb-feedback"><img src="https://agentmods.dev/badge/skills/themind-ai/fluid-db/fluiddb-feedback.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00030 | $0.01004 |
| Opus 5.5 | $0.00012 | $0.00402 |
| Sonnet 5.5 | $0.00006 | $0.00201 |
| Haiku 4.5 | $0.00003 | $0.00100 |
Grade A, and why
fluiddb-feedback 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 18d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FluidDB feedback
Report a specific observation about an exact tool, command, skill, page or API. Keep the summary to 1–3 sentences.
Feedback is sent to the FluidDB team at https://hivenet.app/v1/feedback, outside conversation memory. Send only
synthetic or deliberately sanitized examples; never include identities, secrets, private memories or long transcripts.
Do not submit speculative failures. A skill does not expand the user's authorization to share data externally.
Choose the available surface
- MCP: call
fluiddb_feedbackwhen advertised. Its arguments supportfeedback,category,subject,eval,memoryCase,resume,questionandidempotencyKey. - CLI:
fluiddb feedback --category mcp --subject fluiddb_recall "<specific observation>". - SDK:
Feedback.create().submit(report)from@fluiddb/fluiddb/feedback. - Without FluidDB's CLI, use the keyless HiveNet command:
DO_NOT_TRACK=1 npx --yes hivenet@latest --to fluiddb --category cli --subject "<exact command>" "<specific, actionable feedback>"
Categories: tool, skill, prompt, docs, mcp, cli, api, model, ux, other.
Use the full command, docs URL, exact MCP tool name or API method as the subject.
Without shell access or an in-band tool, the keyless MCP endpoint is https://hivenet.app/mcp/submit;
its submit_feedback tool accepts to: "fluiddb".
Failed tasks become evaluation candidates
After real effort, or when success required a workaround, include a reproducible task and a concrete judge criterion:
fluiddb feedback --category mcp --subject fluiddb_recall \
--task "Save a synthetic move from city A to city B, then ask where the person lives." \
--expected "Return city B with the correction's source." \
--actual "Returned the superseded city A." --attempts 2 \
"Recall selected the superseded address in this synthetic reproduction."
That command is an example, not an observed failure. Replace it with what actually happened. --mistake is optional.
The same flags work with npx --yes hivenet@latest --to fluiddb.
For more detail, use fluiddb feedback --input report.json (or --input -). JSON accepts an eval object with
task, expected, actual, optional mistake and attempts; optional memoryCase describes operation,
challenge, adapter, and aggregate turns/statements counts. No raw memories belong in those fields.
The team curates reports into tests; sending one does not mean a regression has been verified or fixed.
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.
- 18d ago First seen · 73 lines · 30 tokens per session scan A af1fb94acbc6
fluiddb-feedback is a skill published in the GitHub repository TheMind-AI/fluid-db (113 stars, last pushed 16d ago), licensed Apache-2.0. It adds 30 tokens to every session and 1,004 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-29.
Other skills, from other repositories
pinecone:full-text-search
Create, ingest into, and query a Pinecone full-text-search (FTS) document index using the graduated document-schema API (Python SDK 10.0.0, API version 2026-07). Use when the user or agent asks to build a text search index on Pinecone, add dense or sparse vector fields, ingest documents, construct scoreby clauses…
pinecone:quickstart
Interactive Pinecone quickstart for new developers. Choose between two paths - Database (create an integrated index, upsert data, and query using Pinecone MCP + Python) or Assistant (create a Pinecone Assistant for document Q&A). Use when a user wants to get started with Pinecone for the first time or wants a guided…
pinecone:cli
Guide for using the Pinecone CLI (pc) to manage Pinecone resources from the terminal. The CLI supports ALL index types (standard, integrated, sparse) and all vector operations — unlike the MCP which only supports integrated indexes. Use for batch operations, vector management, backups, namespaces, CI/CD automation…
pinecone:mcp
Reference for the Pinecone MCP server tools. Documents all available tools - list-indexes, describe-index, describe-index-stats, create-index-for-model, upsert-records, search-records, cascading-search, and rerank-documents. Use when an agent needs to understand what Pinecone MCP tools are available, how to use them…
pinecone:help
Overview of all available Pinecone skills and what a user needs to get started. Invoke when a user asks what skills are available, how to get started with Pinecone, or what they need to set up before using any Pinecone skill.
help
Overview of all available Pinecone skills and what a user needs to get started. Invoke when a user asks what skills are available, how to get started with Pinecone, or what they need to set up before using any Pinecone skill.