Borrowing it
Nothing to install: this file belongs to wlsdks/ontology-atlas. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/wlsdks/ontology-atlas/main/.agents/skills/gate-probe/SKILL.mdgit clone --depth 1 https://github.com/wlsdks/ontology-atlasWrote 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/wlsdks/ontology-atlas/gate-probe)<a href="https://agentmods.dev/skills/wlsdks/ontology-atlas/gate-probe"><img src="https://agentmods.dev/badge/skills/wlsdks/ontology-atlas/gate-probe/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/wlsdks/ontology-atlas/gate-probe"><img src="https://agentmods.dev/badge/skills/wlsdks/ontology-atlas/gate-probe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00034 | $0.00796 |
| Opus 5 | $0.00017 | $0.00398 |
| Sonnet 5 | $0.00007 | $0.00159 |
| Haiku 4.5 | $0.00003 | $0.00080 |
Grade A, and why
gate-probe 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.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gate probe
A green gate may be protecting the product or looking at nothing. Deliberately breaking the protected property is how to tell.
- A gate is an automated check that blocks a violation: lint, contract test, e2e spec, or CI step.
- A probe is a defect planted on purpose to prove that gate turns red.
This repository has shipped gates that searched generated prose instead of the screen, stayed green after the subject was deleted, checked only a function name, matched zero files, or were invoked by no workflow. None had been probed.
0. State the property
Write one sentence describing the product fact the gate protects. Distinguish the fact from its implementation. “The three installation stages remain reachable” is a property; “scroll equals zero” is an implementation detail.
1. Inventory before enabling
For a new rule, count every current hit and classify it by pattern and legitimacy. Confirm the real violations fit one pull request. Hundreds of new warnings are noise that hides existing signal. A global raw-shadow ban once raised warnings from 144 to 548; a measured selector found five actual defects.
If signal cannot be separated from noise, do not create the rule. Record the inventory and why the gate was rejected.
2. Plant the defect and require RED
Temporarily restore the exact defect or insert one violating line. Run the gate. If it stays green, the gate does not exist.
- Change only the probe line; never use
git checkout -- <file>and erase other work. - Confirm the failure message identifies what and where to fix.
- Probe every independently protected condition.
- Restore the line immediately and require GREEN again.
3. Block idle scans
A scan over zero subjects is always green. Count the subjects and fail at zero. For glob-based rules, prove the glob matches real files. A ratchet baseline that would fail when the scan narrows is another valid anti-idle layer.
expect(keys.length).toBeGreaterThan(0);
expect(measured, 'the collector measured nothing').toBeGreaterThan(3);
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 · +2 lines a74532177190
- 11d ago First seen · 89 lines · 34 tokens per session scan A 63e6f4ecb65d
gate-probe is a skill published in the GitHub repository wlsdks/ontology-atlas (103 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 796 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 2026-08-30.
Other skills, from other repositories
environment-to-production-release-protocol
Use this skill when a Power Platform or Dynamics 365 solution must progress through a structured dev-to-test-to-production release pipeline using managed solutions and Power Platform pipelines, when rollback readiness must be verified before go-live, or when a deployment approval gate must be enforced. Defines the…
argo-rollouts-progressive-delivery-review
Use this skill when reviewing Argo Rollouts progressive delivery configuration. Trigger when the user asks about canary or blue-green Rollout strategy correctness, AnalysisTemplate success/failure conditions, traffic weighting provider alignment, canaryService isolation, PDB deadlock risk with Rollout maxSurge…
ontology-golden-case-testing
A testing method for an ontology, which is a structured model of business concepts and rules. It starts with real business questions and expected answers, then adds boundary, missing-data, conflict, permission, and regression tests.
validation-harness-design
Use when designing repository validation commands, doctor scripts, test matrices, JSON or JUnit outputs, CI gates, smoke checks, or harness command surfaces.
ontology-shacl-validator
Validate ontology outputs through SHACL-oriented checks, structural issue reporting, and release-readiness notes tied to competency questions, evidence quality, and unresolved modeling risks.
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.