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 dimknaf/braindb --skill braindb-agentgit clone --depth 1 https://github.com/dimknaf/braindbWrote 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/dimknaf/braindb/braindb-agent)<a href="https://agentmods.dev/skills/dimknaf/braindb/braindb-agent"><img src="https://agentmods.dev/badge/skills/dimknaf/braindb/braindb-agent/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/dimknaf/braindb/braindb-agent"><img src="https://agentmods.dev/badge/skills/dimknaf/braindb/braindb-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 findings, up to medium
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 →
- medium Data Exfiltration · line 24 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Excessive Agency · line 115 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Memory Poisoning · line 119 Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.Fix: Do not allow untrusted input to persist in agent memory or context. Validate all content before storing and implement memory isolation between sessions.
- medium Excessive Agency · line 143 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 159 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Prompt Injection · line 159 Subtle instructions detected that may alter agent decision-making or introduce hidden biases.Fix: Review content for implicit steering or bias. Ensure instructions are explicit and align with the skill's stated purpose.
- medium Data Exfiltration · line 178 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00040 | $0.03085 |
| Opus 5.5 | $0.00016 | $0.01234 |
| Sonnet 5.5 | $0.00008 | $0.00617 |
| Haiku 4.5 | $0.00004 | $0.00309 |
Grade A, and why
braindb-agent scanned grade A with 1 finding 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
!`curl -sf http://localhost:8000/health > /dev/null 2>&1 && echo "OK" || echo "BRAINDB_DOWN"` How it starts
The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BrainDB Memory Agent
BrainDB has its own internal agent (OpenAI Agents SDK with pluggable provider via LLM_PROFILE; defaults to DeepInfra's google/gemma-4-31B-it) that handles all memory operations. You don't call individual endpoints — you ask the agent in plain English via one endpoint: POST http://localhost:8000/api/v1/agent/query.
Health check:
!curl -sf http://localhost:8000/health > /dev/null 2>&1 && echo "OK" || echo "BRAINDB_DOWN"
If the output contains BRAINDB_DOWN, the memory database is not running. Do this:
- Ask the user: "BrainDB isn't running. Do you want me to start it for you?"
- Find the braindb repo — look for a directory that has ALL of these:
docker-compose.ymlat the rootbraindb/main.pypyproject.tomlwithname = "braindb"Search in: current dir, parent dirs (up to 3 levels), common locations like~/source/repos/**/braindb/.
- Start it:
cd <braindb-path> && docker compose up -d - Cache the path:
echo "<braindb-path>" > ~/.claude/skills/braindb-agent/.repo_path - Wait for it: poll
curl -sf http://localhost:8000/healthfor up to 30 seconds. - If healthy, proceed. If the user declines or start fails, proceed WITHOUT memory.
TOOL PRIORITY (read this first)
The agent has a clear order of tools it should reach for. When you phrase a request, lean into the sophisticated tools — don't ask it to "run SQL" for anything to do with recall or understanding.
- Query-driven recall — "what do we know about X?" → the agent calls
/memory/context(keyword-mediated fuzzy + embedding + graph + ranking, with diversity quotas). The default for ALL discovery and understanding. - Entity-driven neighbourhood — the agent's
view_treereturns a nested JSON tree (root keyed byentity_type,childrenarrays per node, 1-N hops out, keyword + retired-wiki noise filtered by default,_truncatedmarker if more remain). Especially useful when an entity ID is already in hand — often sharper than another query about the same entity. On hub entities passmax_depth=3for narrative chains. - Multi-step investigation — "investigate / disambiguate / resolve X" → the agent delegates to a subagent. Keeps the main context clean.
- Direct lookups —
view_entity_relations,get_entity,list_entitiesfor narrow questions. search_sql⚠ exception only — for explicit aggregates (counts, GROUP BY, activity-log joins). Never for finding / understanding / "what's related to" — those are jobs for the tools above.
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.
- 5d ago Changed cd3af9c147f3
- 1mo ago First seen · 242 lines · 40 tokens per session scan A 92296a586c4a
braindb-agent is a skill published in the GitHub repository dimknaf/braindb (112 stars, last pushed 5d ago), licensed Apache-2.0. It adds 40 tokens to every session and 3,085 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
graph-workflow
Exact mutation, revision, relationship, and document-tree rules for the Understanding Graph. Use when persisting or changing graph state. This is a write-contract reference, not a required thinking loop.
orient
Re-enter relevant graph context when beginning a session, changing projects, or when the user explicitly asks for orientation. Use only when prior graph state could affect the work; it is not a ritual for every conversation.
understanding-work
Use an available Understanding Graph or Undergraph MCP as the persistent medium for substantive reading, research, writing, coding, design, diagnosis, decisions, and other knowledge work. Trigger whenever a user asks for meaningful work in a graph-backed project, even if they do not explicitly say “use the graph.” Let…
quality-check
Inspect graph structure when the user asks for a check or when a concrete structural problem may be affecting the work. Treat metrics as diagnostics, never as quotas or semantic-quality scores.
agent-wiki
Manage a structured knowledge base with immutable raw sources and a mutable wiki layer. Use this skill whenever the user mentions knowledge base, wiki, raw documents, importing documents (Confluence, Jira, URLs, files), searching knowledge, code parsing (COBOL), or asks to add/read/write/search/lint knowledge. Also…
harness-creator
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…