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 kennethkhoocy/applied-micro-skills --skill llm-gold-bound-failure-checkgit clone --depth 1 https://github.com/kennethkhoocy/applied-micro-skillsWrote 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/kennethkhoocy/applied-micro-skills/llm-gold-bound-failure-check)<a href="https://agentmods.dev/skills/kennethkhoocy/applied-micro-skills/llm-gold-bound-failure-check"><img src="https://agentmods.dev/badge/skills/kennethkhoocy/applied-micro-skills/llm-gold-bound-failure-check/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/kennethkhoocy/applied-micro-skills/llm-gold-bound-failure-check"><img src="https://agentmods.dev/badge/skills/kennethkhoocy/applied-micro-skills/llm-gold-bound-failure-check.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 | $0.00182 | $0.01257 |
| Opus 5 | $0.00091 | $0.00629 |
| Sonnet 5 | $0.00036 | $0.00251 |
| Haiku 4.5 | $0.00018 | $0.00126 |
Grade A, and why
llm-gold-bound-failure-check 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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM Gold-Bound Failure Check
Problem
When an LLM scoring pipeline over-predicts one label, the reflex fix is a prompt clarification ("score positive ONLY when..."). But if the gold standard itself does not separate the texts you want excluded from the texts it labels positive, the revision removes true and false positives together. The pilot fails, the spend is wasted, and — worse — an un-gated adoption would have silently destroyed recall in production.
Context / Trigger Conditions
- A domain/label shows precision ≪ recall (e.g. P 0.46 / R 0.96) against gold
- A prompt edit is proposed to exclude a specific text type (boilerplate, affirmative-program language, non-risk framing)
- The label's gold council/inter-rater agreement was already the weakest (κ below ~0.6 is the warning sign that the construct is contested)
Solution
Step 0 — the ~$0 check, BEFORE building anything: read a sample of gold POSITIVES for the weak label and ask: do they contain the feature the revision would exclude? Compare them side-by-side with the false positives.
- Gold positives and false positives are the same kind of text → the failure is gold-bound. Stop. No prompt passes a gold-scored gate. The levers are: (a) re-adjudicate the construct with the gold's owners (changes the gold, not the scores), or (b) re-interpret the shipped measure honestly (e.g. "discussion salience" instead of "risk exposure") in downstream analyses.
- Gold positives clearly differ from the false positives → a prompt revision is plausible; proceed to a gated pilot.
Gated pilot design (verified):
- Split gold into tune/holdout halves, stratified on the weak label's positives; fixed seed.
- Draft ONE surgical edit from tune-half errors only — byte-identical elsewhere; verify the diff reverses cleanly.
- Pre-register the gate on the holdout BEFORE scoring: target-label thresholds (e.g. precision ≥ X AND recall ≥ Y) plus a perturbation tolerance for untouched labels (e.g. within 0.03 F1 / 0.06 κ of a same-serving-rev fresh baseline).
- Score everything fresh under both prompts (same model revision, same day — this doubles as the drift control). Never write through the production cache layer.
- Adopt only on a full pass; a REJECT is a valid, cheap outcome.
What ships with it
1 file 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.
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 · 102 lines · 182 tokens per session scan A c6fd259d50b7
llm-gold-bound-failure-check is a skill published in the GitHub repository kennethkhoocy/applied-micro-skills (27 stars, last pushed 7d ago), licensed MIT. It adds 182 tokens to every session and 1,257 once invoked, about $0.0009 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
baoyu-danger-gemini-web
Generates images and text via reverse-engineered Gemini Web API. Supports text generation, image generation from prompts, reference images for vision input, and multi-turn conversations. Use when other skills need image generation backend, or when user requests "generate image with Gemini", "Gemini text generation"…
understand-knowledge
Analyze a Karpathy-pattern LLM wiki knowledge base and generate an interactive knowledge graph with entity extraction, implicit relationships, and topic clustering.
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…
AI & LLM Security
LLM and AI application security testing — prompt injection, jailbreak resistance, OWASP LLM Top 10 (2025), RAG and agent/tool-use security, model supply chain, and AI red teaming for authorized assessments.
auto-test-code
A structured process for critically reviewing and testing software code. It records review findings, test plans, commands, results, and supporting files in a project workspace.
auto-test-skill
A structured process for critically testing and improving a coding skill. It records test plans, findings, fixes, and quality checks in files that can be reviewed later.