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 ActiveInferenceInstitute/GEO-INFER --skill geo-infer-commsgit clone --depth 1 https://github.com/ActiveInferenceInstitute/GEO-INFERWrote 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/activeinferenceinstitute/geo-infer/geo-infer-comms)<a href="https://agentmods.dev/skills/activeinferenceinstitute/geo-infer/geo-infer-comms"><img src="https://agentmods.dev/badge/skills/activeinferenceinstitute/geo-infer/geo-infer-comms/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/activeinferenceinstitute/geo-infer/geo-infer-comms"><img src="https://agentmods.dev/badge/skills/activeinferenceinstitute/geo-infer/geo-infer-comms.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 | $0.00037 | $0.00979 |
| Opus 5 | $0.00018 | $0.00490 |
| Sonnet 5 | $0.00007 | $0.00196 |
| Haiku 4.5 | $0.00004 | $0.00098 |
Grade A, and why
geo-infer-comms 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 today.
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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- AGENTS.md 1.3 KB
- config/AGENTS.md 1.2 KB
- config/comms_config.yaml 4.3 KB
- config/README.md 799 B
- docs/AGENTS.md 1.1 KB
- docs/api_schema.yaml 24 KB
- docs/README.md 793 B
- examples/AGENTS.md 1.2 KB
- examples/basic_usage.py 9.5 KB runs code
- examples/README.md 1.0 KB
- pyproject.toml 3.1 KB
- README.md 995 B
- requirements.txt 173 B
- setup.py 38 B runs code
- src/AGENTS.md 1.1 KB
- src/geo_infer_comms/__init__.py 16 KB runs code
- src/geo_infer_comms/AGENTS.md 1.2 KB
- src/geo_infer_comms/api/__init__.py 376 B runs code
- src/geo_infer_comms/api/AGENTS.md 1.2 KB
- src/geo_infer_comms/api/README.md 1.1 KB
- src/geo_infer_comms/api/rest_api.py 24 KB runs code
- src/geo_infer_comms/api/websocket_api.py 29 KB runs code
- src/geo_infer_comms/core/__init__.py 1.6 KB runs code
- src/geo_infer_comms/core/AGENTS.md 1.3 KB
- src/geo_infer_comms/core/channels.py 32 KB runs code
- src/geo_infer_comms/core/collaboration.py 30 KB runs code
- src/geo_infer_comms/core/events.py 34 KB runs code
- src/geo_infer_comms/core/messaging.py 26 KB runs code
- src/geo_infer_comms/core/notifications.py 34 KB runs code
- src/geo_infer_comms/core/README.md 1.7 KB
- src/geo_infer_comms/core/spatial_routing.py 36 KB runs code
- src/geo_infer_comms/core/streaming.py 32 KB runs code
- src/geo_infer_comms/integrations/__init__.py 630 B runs code
- src/geo_infer_comms/integrations/AGENTS.md 1.2 KB
- src/geo_infer_comms/integrations/email_providers.py 15 KB runs code
- src/geo_infer_comms/integrations/README.md 1.1 KB
- src/geo_infer_comms/models/__init__.py 2.4 KB runs code
- src/geo_infer_comms/models/AGENTS.md 1.2 KB
- src/geo_infer_comms/models/message.py 16 KB runs code
- src/geo_infer_comms/models/README.md 1.5 KB
- src/geo_infer_comms/models/spatial.py 18 KB runs code
- src/geo_infer_comms/README.md 1.1 KB
- src/geo_infer_comms/utils/__init__.py 1.6 KB runs code
- src/geo_infer_comms/utils/AGENTS.md 1.2 KB
- src/geo_infer_comms/utils/README.md 1.7 KB
- src/geo_infer_comms/utils/validation.py 18 KB runs code
- src/README.md 792 B
- tests/AGENTS.md 1.2 KB
- tests/conftest.py 56 B runs code
- tests/integration/AGENTS.md 1.2 KB
- tests/integration/README.md 835 B
- tests/integration/test_integration.py 4.1 KB runs code
- tests/integration/test_websocket_broadcast.py 6.7 KB runs code
- tests/README.md 1.8 KB
- tests/unit/AGENTS.md 1.5 KB
- tests/unit/README.md 1.2 KB
- tests/unit/test_channels.py 3.2 KB runs code
- tests/unit/test_collaboration_sessions.py 9.2 KB runs code
- tests/unit/test_core.py 1.6 KB runs code
- tests/unit/test_email_providers.py 1.8 KB runs code
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.
- today Changed 470b9804a131
- 5d ago Changed · +40 lines · -6 tokens per session 248e9d4df751
- 7d ago First seen · 63 lines · 43 tokens per session scan A 058281258864
geo-infer-comms is a skill published in the GitHub repository ActiveInferenceInstitute/GEO-INFER (15 stars, last pushed today), with no licence file. It adds 37 tokens to every session and 979 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 2026-09-04.
Other skills, from other repositories
domain-driven-design
DDD tactical patterns for complex business modeling including entities, value objects, aggregates, domain services, repositories, specifications, and bounded contexts. Python dataclass implementations with TypeScript alternatives. Use when building rich domain models, enforcing invariants, or separating domain logic…
gdal-api
Use when programming against GDAL/OGR in C, C++, Python, or .NET for raster/vector I/O, coordinate transformation, or custom geospatial algorithms. GDAL API: low-level programming interface for reading/writing 70+ geospatial formats.
ddd-aggregate-modeling
Guides aggregate modeling decisions for DDD services: aggregate root boundaries, child entity vs value object decisions, invariants, snapshot/primitives mapping, specification/criteria usage, and repository contract design. Invoked when the user asks to model or refactor domain entities and aggregate behavior.
loguru
A guide to Loguru, a Python library for writing application logs. Logs are records of events, errors, and useful status information produced while a program runs.
nest-generate
A code-generation guide for creating NestJS modules, controllers, services, and data-transfer objects in the trading-assistant backend. NestJS is a framework for building Node.js server applications.
api-contract
A review guide for checking whether a frontend and backend follow the same OpenAPI 3.0 API contract. An API contract is a shared document that defines request paths, inputs, responses, errors, and data types.