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 zajalist/hayba --skill hayba-pcgex-output-auditgit clone --depth 1 https://github.com/zajalist/haybaWrote 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/zajalist/hayba/hayba-pcgex-output-audit)<a href="https://agentmods.dev/skills/zajalist/hayba/hayba-pcgex-output-audit"><img src="https://agentmods.dev/badge/skills/zajalist/hayba/hayba-pcgex-output-audit/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/zajalist/hayba/hayba-pcgex-output-audit"><img src="https://agentmods.dev/badge/skills/zajalist/hayba/hayba-pcgex-output-audit.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 | $0.00034 | $0.00383 |
| Opus 5.5 | $0.00014 | $0.00153 |
| Sonnet 5.5 | $0.00007 | $0.00077 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
hayba-pcgex-output-audit 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 13d 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.
What it actually says
Audit generated PCG output
When to use
Use after graph creation, edit, or regeneration, especially when a tool reports success while the viewport looks empty. Establish the target actor/component and expected output type.
Tool routing
- Read the graph and run
hayba_validate_pcg_graphfor structural faults. This does not establish output quantity or correctness. - Prefer
pcg_cook_and_waitfor a bound actor expected to produce instances. Inspect its per-mesh instance counts and freshness data.hayba_execute_pcg_graphorpcg_execute_graphonly establishes that execution was triggered.pcg_read_node_outputmay read a stale inspection cache and cannot disprove fresh instance output. - Capture with
editor_capture_viewport, inspect representative positions, and runvalidator_runafter scene generation. - When this audit accepts a cook that changed persistent map content, save the exact active map with
level_save, inspect saved, dirty, and verified status, then re-read the bound actor and generated counts. If it was only an inspection, state that no map save was needed. If persistence remains uncertain, mark the generated result unsaved and route it to hayba-world-save-integrity.
Evidence
Report graph path, target component, expected output, fresh counts by mesh, viewport observation, and validation findings. A zero count fails an instance-generation goal. A nonzero count does not establish visual composition or frame-time safety; route those questions to the relevant skill. Do not retry a cook without checking whether a prior call already changed the scene.
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.
- 13d ago First seen · 25 lines · 34 tokens per session scan A be8f9f194980
hayba-pcgex-output-audit is a skill published in the GitHub repository zajalist/hayba (13 stars, last pushed 3d ago), licensed MIT. It adds 34 tokens to every session and 383 once invoked, about $0.0001 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 2026-10-04.
Other skills, from other repositories
debug-unreal-pie-with-python
Control and debug one in-process Unreal Engine Play In Editor or Simulate session through Loomle Python after applying the use-unreal-python safety workflow. Use when reproducing gameplay, querying runtime Actors or components, invoking gameplay APIs, checking state across frames, or managing PIE start and stop.
debug-issue
Systematic Godot debugging decision trees for physics, signals, rendering, navigation, and input issues.
unreal-performance-profiling
Use when an Unreal Engine project has low frame rate, hitches, stalls, memory growth, long loads, excessive draw calls, shader or overdraw cost, expensive AI or Blueprint work, or needs an evidence-based performance budget.
migrate-oxlint
Guide for migrating a project from ESLint to Oxlint. Use when asked to migrate, convert, or switch a JavaScript/TypeScript project's linter from ESLint to Oxlint.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
repro-public
Reproduce a bug in the public-facing rendered site (not the admin). Attach a container, start the demo dev server, drive public routes with agent-browser, and capture the reproduction as screenshots plus a replayable transcript.