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-testgit 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-test)<a href="https://agentmods.dev/skills/activeinferenceinstitute/geo-infer/geo-infer-test"><img src="https://agentmods.dev/badge/skills/activeinferenceinstitute/geo-infer/geo-infer-test/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-test"><img src="https://agentmods.dev/badge/skills/activeinferenceinstitute/geo-infer/geo-infer-test.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 | $0.00042 | $0.00753 |
| Opus 5 | $0.00021 | $0.00377 |
| Sonnet 5 | $0.00008 | $0.00151 |
| Haiku 4.5 | $0.00004 | $0.00075 |
Grade A, and why
geo-infer-test 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 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.
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.
- .gitignore 123 B
- AGENTS.md 2.9 KB
- build_package_wheels.py 12 KB runs code
- check_coverage_floor.py 3.8 KB runs code
- config/AGENTS.md 1.2 KB
- config/example.yaml 2.4 KB
- config/import-probes.ini 154 B
- config/README.md 996 B
- coverage_baseline_metric.py 2.2 KB runs code
- coverage_baseline.json 4.1 KB
- demo/__init__.py 75 B runs code
- demo/crescent_city_civic_intel_demo.py 28 KB runs code
- demo/README.md 1.5 KB
- demo/test_crescent_city_civic_intel_demo.py 8.1 KB runs code
- docs/AGENTS.md 1.3 KB
- docs/api_reference.md 2.9 KB
- docs/examples/advanced_example.md 1.3 KB
- docs/examples/basic_example.md 1.3 KB
- docs/getting_started.md 2.5 KB
- docs/gnn_continuation_2026_09.md 14 KB
- docs/gnn_space_time_2026_09.md 5.3 KB
- docs/index.md 3.8 KB
- docs/README.md 1.1 KB
- docs/secret_scan_policy.md 3.3 KB
- examples/AGENTS.md 1.2 KB
- examples/basic_testing_example.py 8.0 KB runs code
- examples/README.md 1.1 KB
- import_probe.py 3.1 KB runs code
- measure_module_coverage.py 6.0 KB runs code
- orchestrator_coverage_metric.py 1.6 KB runs code
- preview_receipt_metric.py 5.2 KB runs code
- pyproject.toml 3.8 KB
- README.md 3.7 KB
- render_lane_metric.py 14 KB runs code
- requirements.txt 521 B
- rewrite_readme_agents.py 53 KB runs code
- run_model_audit.py 4.7 KB runs code
- run_unified_tests.py 18 KB runs code
- secret_scan_metric.py 3.3 KB runs code
- setup.py 38 B runs code
- src/AGENTS.md 1.2 KB
- src/geo_infer_test/__init__.py 1.8 KB runs code
- src/geo_infer_test/AGENTS.md 1.2 KB
- src/geo_infer_test/core/__init__.py 1.4 KB runs code
- src/geo_infer_test/core/AGENTS.md 1.3 KB
- src/geo_infer_test/core/log_integration.py 13 KB runs code
- src/geo_infer_test/core/module_health.py 8.3 KB runs code
- src/geo_infer_test/core/performance_monitor.py 11 KB runs code
- src/geo_infer_test/core/README.md 2.0 KB
- src/geo_infer_test/core/test_discoverer.py 12 KB runs code
- src/geo_infer_test/core/test_orchestrator.py 8.7 KB runs code
- src/geo_infer_test/core/test_runner.py 19 KB runs code
- src/geo_infer_test/core/validators.py 39 KB runs code
- src/geo_infer_test/models/__init__.py 0 B runs code
- src/geo_infer_test/models/AGENTS.md 1.2 KB
- src/geo_infer_test/models/README.md 1007 B
- src/geo_infer_test/models/types.py 918 B runs code
- src/geo_infer_test/README.md 1.6 KB
- src/geo_infer_test/testing.py 8.9 KB runs code
- src/README.md 971 B
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 d6a2ed233e1d
- 7d ago First seen · 95 lines · 42 tokens per session scan A c7f87a6041d9
geo-infer-test is a skill published in the GitHub repository ActiveInferenceInstitute/GEO-INFER (15 stars, last pushed 3d ago), with no licence file. It adds 42 tokens to every session and 753 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
template-formal
Strongly-typed multiagent ant-robot colony exemplar — ADTs, session-typed protocols, affine-discipline resource handles, storage-as-functor framing, Active-Inference-flavored decision loop, mypy-as-oracle negative controls.
nexus-testing
Use for flaky or nondeterministic tests, especially local-vs-CI inconsistencies. Trigger on intermittent failures, race/timing symptoms, retry-only greens, or unexplained skip/xfail markers. Output should isolate reproducible cause, narrowest durable fix, and prevention guidance. When in doubt, use this skill.
test-gap-review
Review whether existing tests and verification credibly prove a scoped behavior contract. Use during validation when evidence may omit important behavior or provide false confidence.
agent-browser
Browser automation through the agent-browser CLI for websites, local web apps, forms, screenshots, scraping, QA, and exploratory testing. Use when Codex needs real browser interaction, visual evidence, accessibility snapshots, video recording, or browser-based checks.
crap-index-assess
Assess method-level change risk with the Change Risk Anti-Patterns (CRAP) index and recommend focused testing or complexity reduction. Use when a repository configures CRAP measurement, cyclomatic complexity and automated test coverage data are available, or a user asks what CRAP means, how to calculate or interpret…
behavior-implement
Implement behavior through a red-green-refactor cycle when focused automated tests are proportionate. Use for product behavior changes and for engineering tooling and infrastructure only when native checks are insufficient and concrete complexity or failure risk warrants dedicated tests.