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 joelbrilliant/agentic-delivery-skills --skill orchestrated-agentic-deliverygit clone --depth 1 https://github.com/joelbrilliant/agentic-delivery-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/joelbrilliant/agentic-delivery-skills/orchestrated-agentic-delivery)<a href="https://agentmods.dev/skills/joelbrilliant/agentic-delivery-skills/orchestrated-agentic-delivery"><img src="https://agentmods.dev/badge/skills/joelbrilliant/agentic-delivery-skills/orchestrated-agentic-delivery/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/joelbrilliant/agentic-delivery-skills/orchestrated-agentic-delivery"><img src="https://agentmods.dev/badge/skills/joelbrilliant/agentic-delivery-skills/orchestrated-agentic-delivery.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 | $0.00068 | $0.01234 |
| Opus 5 | $0.00034 | $0.00617 |
| Sonnet 5 | $0.00014 | $0.00247 |
| Haiku 4.5 | $0.00007 | $0.00123 |
Grade A, and why
orchestrated-agentic-delivery 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 11d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrated Agentic Delivery
Overview
Use this skill to run agentic work as a real delivery lane instead of a pile of helpful model outputs.
The roles are separate:
- Orchestrator: frames the task, controls scope, routes work, judges final evidence.
- Builder: implements the approved slice and owns the primary diff until review.
- Reviewer: adversarially reviews the builder's work and may enter an explicit fix pass.
- Final judge: the orchestrator signs off against the brief, diff, review, fixes, and evidence.
Runtime does not matter. The builder or reviewer can be any coding agent, chat agent, custom harness, or subagent. Accountability follows the role, not the tool.
When to Use
Use this skill for:
- production-bound features or bug fixes with more than one role;
- work where an orchestrator dispatches builders or reviewers;
- multi-agent workflows across coding agents or subagents;
- reviewer-fix flows where the reviewer is allowed to repair findings;
- final signoff after build plus review;
- any task where same-model builder and reviewer echo-chamber risk matters.
Do not use this for one-off answers, throwaway scripts, or prototypes with no review gate.
Mandatory Companion
Load bulletproof-building-and-review during:
- production-bound building self-signoff;
- adversarial review;
- reviewer-fix mode;
- closing findings as non-issues;
- final orchestrator signoff.
This skill defines who does what. bulletproof-building-and-review defines how to prove it is not bullshit.
Core Rules
- One slice, one primary builder. Extra builders are allowed only for independent slices with non-overlapping write sets.
- Reviewer is not a stealth co-builder. Reviewer fixes only after writing findings and entering explicit reviewer-fix mode.
- Final signoff belongs to the orchestrator. Builders and reviewers provide evidence. They do not self-merge by vibes.
- Design approval gates stay real. If design or spec is in scope, get signoff before implementation.
- Fix root causes. Do not layer workarounds unless the brief explicitly accepts that tradeoff.
- Runtime is not authority. Every model and harness needs the same evidence discipline.
- No invisible work. When the platform supports visible run IDs, tasks, PRs, commits, or transcripts, use them.
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.
- 11d ago First seen · 151 lines · 68 tokens per session scan A 54f7d84fa74c
orchestrated-agentic-delivery is a skill published in the GitHub repository joelbrilliant/agentic-delivery-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 68 tokens to every session and 1,234 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
cuopt-numerical-optimization-formulation
LP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.
cupynumeric-migration-readiness
Pre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment…
deepstream-sop
Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the…
hsb-ip-packetizer
Choose or explain HSB Sensor RX packetizer fields for HOLOLINKdef.svh. Do not use for full defs, validation, or runtime APB programming.
nemo-mbridge-perf-expert-parallel-overlap
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlapmoeexpertparallelcomm, delaywgradcompute, and flex dispatcher backends such as DeepEP and HybridEP.
deepstream-run-mv3dt
Run and operate the DeepStream Multi-View 3D Tracking reference app, also known as MV3DT. Use when the user asks to set up prerequisites, run shipped MV3DT samples, run Multi-View 3D Tracking on custom synchronized MP4 datasets, import camera calibration, delegate missing calibration to AutoMagicCalib, inspect OSD or…