Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/chris-page-gov/mcp-geonpx agentmods add skills/chris-page-gov/mcp-geo/mcp-geo-obsidian-kbWrote 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/chris-page-gov/mcp-geo/mcp-geo-obsidian-kb)<a href="https://agentmods.dev/skills/chris-page-gov/mcp-geo/mcp-geo-obsidian-kb"><img src="https://agentmods.dev/badge/skills/chris-page-gov/mcp-geo/mcp-geo-obsidian-kb/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/chris-page-gov/mcp-geo/mcp-geo-obsidian-kb"><img src="https://agentmods.dev/badge/skills/chris-page-gov/mcp-geo/mcp-geo-obsidian-kb.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 | $0.00039 | $0.00506 |
| Opus 5.5 | $0.00016 | $0.00202 |
| Sonnet 5.5 | $0.00008 | $0.00101 |
| Haiku 4.5 | $0.00004 | $0.00051 |
Grade A, and why
mcp-geo-obsidian-kb 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 2mo 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Geo Obsidian Knowledge Base
Use this skill when you need to refresh or validate the repo knowledge base
under Obsidian/MCP Geo Knowledge Base/.
Scope
- Canonical tier: checked-in markdown generated from tracked repo content.
- Local overlay tier: ignored, machine-local notes generated from
logs/and session traces when explicitly requested. - Validation: coverage, drift, recursion exclusion, and missing-note checks.
Default commands
Refresh the canonical vault:
python3 scripts/build_obsidian_kb.py \
--mode canon \
--git-ref WORKTREE \
--output-root "Obsidian/MCP Geo Knowledge Base" \
--manifest-out data/knowledge_base/obsidian_kb_manifest.json
Refresh the canonical vault plus local overlay:
python3 scripts/build_obsidian_kb.py \
--mode all \
--git-ref WORKTREE \
--output-root "Obsidian/MCP Geo Knowledge Base" \
--manifest-out data/knowledge_base/obsidian_kb_manifest.json \
--overlay-manifest-out data/knowledge_base/obsidian_kb_overlay_manifest.json \
--include-local-evidence
Validate the canonical manifest:
python3 scripts/validate_obsidian_kb.py \
--manifest data/knowledge_base/obsidian_kb_manifest.json \
--fail-on drift coverage recursion orphan
Maintenance rules
- Never let the generator scan
Obsidian/**. - Treat tracked repo content as the canonical evidence source.
- Keep local traces in
98 Local Overlay/only; do not promote them into the canonical tier unless they are first captured as tracked repo artifacts. - Prefer commit-pinned GitHub links in generated notes.
- When validator drift or coverage failures appear, refresh the vault after the underlying tracked content is updated.
Promotion workflow
- If a local trace becomes durable evidence, write or generate a tracked report, research note, or manifest elsewhere in the repo first.
- Rebuild the canonical vault only after that tracked artifact exists.
- Do not copy speculative interpretation into the knowledge base; keep notes descriptive and evidence-backed.
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.
- 2mo ago First seen · 67 lines · 39 tokens per session scan A 6e51619264ae
mcp-geo-obsidian-kb is a skill published in the GitHub repository chris-page-gov/mcp-geo (3 stars, last pushed 3d ago), licensed MIT. It adds 39 tokens to every session and 506 once invoked, about $0.0002 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 2026-08-31.
mcp-geo-obsidian-kb compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-geo-obsidian-kbchris-page-gov/mcp-geo | Skill | 3 | 3d ago | MIT | A | 39 | Claude Code, Codex |
| orbit-notionnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 117 | Claude Code, Codex |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | 3d ago | Apache-2.0 | A | 123 | Claude Code |
| apify-youtube-transcript-scrapersickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 48 | Claude Code |
| legal-holdanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 68 | Claude Code |
| ppt-reviewOrkas-AI/Orkas | Skill | 9.0k | yesterday | MIT | A | 2 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 6d ago | MIT | A | 33 | Claude Code, Codex |