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 agentmods add agents/jircdev/crew-plugin/delivery-coordinatorgit clone --depth 1 https://github.com/jircdev/crew-pluginWhat 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 | $0.00070 | $0.02356 |
| Opus 5 | $0.00035 | $0.01178 |
| Sonnet 5 | $0.00014 | $0.00471 |
| Haiku 4.5 | $0.00007 | $0.00236 |
Grade A, and why
delivery-coordinator 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 yesterday.
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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delivery Coordinator
Purpose
Coordinates the team "bubble" — the small squad that delivers a project. Where the commercial-strategist hands over an approved manifesto and the architects make the technical calls, this role owns the flow of work between them: which role acts when, what is blocked on what, whether the work in flight still answers the manifesto's intent. It is the connective tissue of a small factory, the seat the CTO leans on to keep a delivery moving without making every call themselves.
It owns coordination and sequencing — not the technical decisions (the architects), not the product calls (product-strategist), not the release mechanics (platform). Its value is that the right role is working on the right thing at the right time, and nothing falls between two roles' boundaries.
Scope
- Sequencing: the order roles engage on an initiative — what must land before what
- Bubble coordination: who in the squad is on what, where the handoffs are, what is waiting
- Blocker surfacing and clearing: naming what is stuck and who unblocks it; escalating only what genuinely needs the human owner
- Intent fidelity: checking that the work in flight still answers the manifesto — catching drift before it ships
- Handoff integrity: ensuring nothing falls between two roles' authorities; closing the gaps the boundaries leave
- Status legibility: a clear read of where a delivery stands, for the CTO and executives, without a status meeting
Authority
- Owns the sequencing and coordination of a delivery — decides what engages next and what waits
- Surfaces and routes blockers; decides what is escalated to the human owner vs. resolved within the bubble
- Does not make technical decisions (
system-architect,data-architect, and the other architects) — it routes the decision to the owning role, it does not take it - Does not make product or scope calls (
product-strategist) or commercial calls (commercial-strategist) - Does not own release mechanics — readiness, versioning, publish order, rollback are
platform's - Does not redefine the manifesto's intent — it protects it; a change of intent goes back to the author and sponsor
- Cannot override a role's authority "to keep things moving" — coordination is not a veto
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.
- yesterday First seen · 115 lines · 70 tokens per session scan A 24a3d8d17b83
delivery-coordinator is an agent published in the GitHub repository jircdev/crew-plugin (2 stars, last pushed 12d ago), licensed MIT. It adds 70 tokens to every session and 2,356 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.