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 dlxeva/fde-operator-os --skill pilot-designergit clone --depth 1 https://github.com/dlxeva/fde-operator-osWrote 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/dlxeva/fde-operator-os/pilot-designer)<a href="https://agentmods.dev/skills/dlxeva/fde-operator-os/pilot-designer"><img src="https://agentmods.dev/badge/skills/dlxeva/fde-operator-os/pilot-designer/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/dlxeva/fde-operator-os/pilot-designer"><img src="https://agentmods.dev/badge/skills/dlxeva/fde-operator-os/pilot-designer.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 | $0.00035 | $0.00661 |
| Opus 5.5 | $0.00014 | $0.00264 |
| Sonnet 5.5 | $0.00007 | $0.00132 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
pilot-designer 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 2mo 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pilot Designer
Use this skill when the main question is:
- what is the smallest credible pilot
- where should AI intervene
- what remains human-owned
- how will the pilot be judged
- what evidence is required before production-readiness review
Scope
Stay focused on bounded pilot design and the G2 Pilot Contract gate.
Primary outputs:
AI Intervention DesignMinimum Viable LoopPOC Acceptance ContractEval PackGovernance And Risk Overlaywhen the AI influences operational action
What To Define
- target bottleneck
- narrow AI surface
- human confirmation boundary
- baseline manual path
- representative tasks and failure classes
- explicit graders and acceptance thresholds
- fallback and rollback conditions
- audit and authority boundary
- operator adoption signal
- production-readiness dependencies
Evidence Requirement
Build pilot cases from observed work where available:
- golden cases
- failure cases
- edge cases
- ambiguous cases
- demo-killing cases
Keep synthetic cases labeled. Carry missing production evidence into the Reality Capture Gate or Production Readiness Review as a blocker.
Production Handoff
The pilot is ready to hand to deployment-readiness when:
- the bounded loop and baseline are stable
- the POC Acceptance Contract is locked
- representative eval cases and regression checks exist
- authority, audit, fallback, and rollback are defined
- the intended operator cohort and adoption signal are known
- remaining launch dependencies are explicit
This handoff does not imply launch approval. deployment-readiness owns the G3 go, conditional-go, or no-go decision.
Do Not Expand Into
- broad account strategy
- full platform architecture before the loop is proven
- organization-wide rollout
- live launch approval
- detailed day-2 operations beyond the pilot boundary and handoff requirements
Completion Standard
A reviewer can explain the bounded pilot, AI and human responsibilities, baseline, representative evals, acceptance and failure criteria, fallback and rollback paths, and the evidence still needed before live use.
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.
- 2mo ago First seen · 105 lines · 35 tokens per session scan A 5d6b77f80fc4
pilot-designer is a skill published in the GitHub repository dlxeva/fde-operator-os (11 stars, last pushed 10d ago), licensed MIT. It adds 35 tokens to every session and 661 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 2026-08-30.
Other skills, from other repositories
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and designs an end-to-end governed agentic analytics solution using Knowledge Catalog and Managed Service for Apache Spark (Lightning Engine). Use when designing data science and analytics workflows across structured and unstructured distributed data (including in S3, Azure Blob, AlloyDB, and…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
finetuning
Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file…