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 perniemann/pnCore --skill pn-api-probegit clone --depth 1 https://github.com/perniemann/pnCoreWrote 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/perniemann/pncore/pn-api-probe)<a href="https://agentmods.dev/skills/perniemann/pncore/pn-api-probe"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-api-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/perniemann/pncore/pn-api-probe"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-api-probe.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 | $0.00044 | $0.02355 |
| Opus 5 | $0.00022 | $0.01177 |
| Sonnet 5 | $0.00009 | $0.00471 |
| Haiku 4.5 | $0.00004 | $0.00235 |
Grade A, and why
pn-api-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 6d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pn-api-probe
Mission
Before committing to a design or build plan, verify that the runtime APIs, library versions, and key enumerations you intend to use actually exist in the target environment. Training data has a cutoff; runtime has ground truth.
When to use
- At the start of
pn-design(step 2, Plan) andpn-build(Phase 0) when the stack involves frequently-updated runtimes (Blender Python API, browser APIs, framework releases, SDK versions). - When a prior session produced unexpected output that could indicate a version mismatch.
- When discovery spec references a specific runtime version (e.g. Blender 4.x, Next.js 15, Node 22).
Instructions
-
Identify the probe targets. From the discovery spec or plan, extract:
- Runtime name and version (e.g.
Blender 4.3,Node 22.x,React 19) - APIs or enumerations in scope (e.g.
bpy.ops.render,bpy.context.scene.render.*,React.use()) - Known deprecation risks (APIs your plan uses that may have changed)
- Runtime name and version (e.g.
-
Probe live. Use available tools to fetch current state:
- Web/framework: Search official changelog, release notes, or docs for the version in scope. Target: official docs site, GitHub releases, MDN.
- Blender Python API: Search the Blender Python API reference for the current version. Check: are the specific
bpy.*calls still present? Any renamed or removed enums? - Node/npm packages: Check the package's npm page or GitHub releases for the version range in use.
- Use web search with version-pinned queries, e.g.
"Blender 4.3 bpy.context.scene.render use_scene_lights".
-
Emit structured output:
{ "runtime_version": "<name and version probed>", "available_apis": [ { "api": "<api or enum>", "status": "confirmed | deprecated | removed | unknown", "notes": "" } ], "deprecated_apis": [ { "api": "<api>", "replacement": "<new api or none>", "notes": "" } ], "version_gaps": [ { "item": "<feature or API>", "expected": "<what plan assumes>", "actual": "<what probe found>", "impact": "blocking | warning | info" } ], "recommendation": "proceed | revise_plan | block" }
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.
- 6d ago First seen · 155 lines · 44 tokens per session scan A 1ac7ec740648
pn-api-probe is a skill published in the GitHub repository perniemann/pnCore (0 stars, last pushed 3d ago), licensed MIT. It adds 44 tokens to every session and 2,355 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 2026-09-03.
Other skills, from other repositories
error-handling
Apply error handling and recovery patterns in JavaScript/TypeScript or Node.js. Use when implementing error handling, retry logic, or when the user mentions domain errors, error recovery, error escalation.
t-800-fix-pack
A defined format and workflow for preparing a fix pack, a document that lists approved changes to an existing artifact.
cocoreview
CocoReview — structured code review with six-severity findings vocabulary, progressive disclosure architecture, and universal anti-pattern baseline. Invoked via $review [file] [--complexity] [--security] [--architecture] [--language ].
firebase-crashlytics
Use when implementing crash reporting, capturing fatal/non-fatal errors, recording isolate/async exceptions, customizing reports, or uploading obfuscated symbols.
flutter-errors
Use when hitting layout errors (RenderFlex overflow, unbounded constraints, RenderBox not laid out), scroll errors, or setState-during-build errors.
identify-key-failures
Synthesize the common stuck points across failed decomposition plans. Use when the current batch of decomposition plans has failed — whether they failed already at direct proving or only after further attempts.