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 nicholasglazer/gnosis-mcp --skill statusgit clone --depth 1 https://github.com/nicholasglazer/gnosis-mcpWrote 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/nicholasglazer/gnosis-mcp/status)<a href="https://agentmods.dev/skills/nicholasglazer/gnosis-mcp/status"><img src="https://agentmods.dev/badge/skills/nicholasglazer/gnosis-mcp/status/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/nicholasglazer/gnosis-mcp/status"><img src="https://agentmods.dev/badge/skills/nicholasglazer/gnosis-mcp/status.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Agent Snooping · line 40 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 | $0.00031 | $0.01789 |
| Opus 5 | $0.00015 | $0.00894 |
| Sonnet 5 | $0.00006 | $0.00358 |
| Haiku 4.5 | $0.00003 | $0.00179 |
Grade A, and why
status 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 10d 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 -fsS http://127.0.0.1:8000/health | jq . How it starts
The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Status
Diagnostic for "something is wrong with gnosis-mcp". Produces a compact report the user can screenshot and paste in an issue.
Usage
/gnosis:status # Full check — connectivity + schema + stats + common failure modes
/gnosis:status quick # Just connectivity
/gnosis:status stats # Document / chunk / embedding counts
/gnosis:status diag # Extended diagnostics (used when something is wrong)
Mode: $ARGUMENTS
Step 1 — connectivity
Preferred path: the MCP itself. If mcp__gnosis__* tools respond, the
server is up and MCP is wired correctly.
mcp__gnosis__get_graph_stats()
If that returns data, skip to Step 2.
MCP tool not available
Two common causes:
- Server not running — for stdio transport, the MCP client should
auto-spawn the server. If not: check
.mcp.json/.claude/mcp.jsonconfig, confirmgnosis-mcpis onPATH. - Server running, but client not connected — restart the editor once MCP config is correct.
Direct CLI check (works independent of MCP wiring):
gnosis-mcp check
Expected output:
Backend: sqlite (SQLite 3.46.0)
Database: /home/<you>/.local/share/gnosis-mcp/docs.db
chunks_table_exists: true (1742 rows)
fts_table_exists: true
sqlite_vec: true
vec_table_exists: true (1742 rows)
links_table_exists: true (812 rows)
embeddings_coverage: 100.0%
If check itself returns errors, stop here — the server can't talk to
its own database. Likely causes:
- DB file doesn't exist →
gnosis-mcp init-db - DB schema old →
gnosis-mcp init-db(idempotent, adds any new columns) - SQLite extension missing (
sqlite_vec: false) →pip install 'gnosis-mcp[embeddings]'
Step 2 — corpus stats
mcp__gnosis__get_graph_stats()
Report in a compact block:
Docs: 412
Chunks: 1,247 (avg 3.0 per doc at current chunk_size)
Orphans: 18 (docs with no graph edges)
Top hubs:
README.md 37 links
docs/tools.md 24 links
docs/config.md 19 links
Edge types:
related 612
content_link 410
git_co_change 225
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.
- 10d ago First seen · 255 lines · 31 tokens per session scan A d14dfc083bfe
status is a skill published in the GitHub repository nicholasglazer/gnosis-mcp (29 stars, last pushed 20d ago), licensed MIT. It adds 31 tokens to every session and 1,789 once invoked, about $0.0002 per session on Opus 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
axiom-swiftdata-migration-diag
Use when SwiftData migrations crash, fail to preserve relationships, lose data, or work in simulator but fail on device - systematic diagnostics for schema version mismatches, relationship errors, and migration testing gaps.
vault
Generate an Obsidian LLM wiki vault from a project's source code and any static documents in raw/.
vault-update
Incrementally update an existing vault — detect code changes via git diff and static file changes via SHA256, then re-analyze and rewrite only affected pages.
backend-patterns
Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes. Use when building or reviewing Node.js, Express, or Next.js API routes and their data access.
database-migrations
Database migration best practices for schema changes, data migrations, rollbacks, and zero-downtime deployments across PostgreSQL, MySQL, and common ORMs (Prisma, Drizzle, Django, TypeORM, golang-migrate). Use when planning or implementing database schema changes.
agent-introspection-debugging
Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry.