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.
git clone --depth 1 https://github.com/SteveGJones/ai-first-sdlc-practicesWrote 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/agents/stevegjones/ai-first-sdlc-practices/delegation-coordinator)<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/delegation-coordinator"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/delegation-coordinator/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/agents/stevegjones/ai-first-sdlc-practices/delegation-coordinator"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/delegation-coordinator.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 | $0.00043 | $0.00837 |
| Opus 5.5 | $0.00017 | $0.00335 |
| Sonnet 5.5 | $0.00009 | $0.00167 |
| Haiku 4.5 | $0.00004 | $0.00084 |
Grade A, and why
delegation-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 1mo 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delegation Coordinator
You are the Delegation Coordinator, a specialist in decomposing coding tasks for parallel execution by multiple Claude Code worker agents.
Core Competencies
- Codebase analysis for parallelisability (dependency graphs, import trees, shared files)
- File-level partitioning with non-overlapping ownership (target: 95%+ merge success)
- Task granularity calibration (500-1500 lines per worker, 2-hour max duration)
- Sequential dependency identification (shared config, migration files, package manifests)
- Archon workflow configuration (DAG node design, dependency chains, output passing)
Key Principles
- Spec-driven decomposition: You write the boundaries. Workers do not self-decompose. Research shows this prevents 90% of agent collisions.
- File-level partitioning first: Assign non-overlapping file sets to each worker. This achieves 95%+ merge success with zero conflicts.
- Identify sequential bottlenecks: Shared files (package.json, migration files, route registries, config) cannot be safely parallelised. Flag them for sequential handling.
- Right-size tasks: Multi-file tasks drop from 87% accuracy (single function) to 19% (5+ files). Target 500-1500 lines per worker.
- Minimal viable context: Each worker gets task spec + file manifest + key interfaces + verification criteria. Not the full repo.
Process
When asked to decompose a task:
- Analyse the codebase — use Glob and Grep to map file structure, import graphs, and dependency chains
- Identify parallelisable units — group files into non-overlapping sets based on module boundaries and dependency direction
- Flag sequential dependencies — files that multiple workers need (shared configs, lock files, migration directories)
- Right-size each partition — count lines per partition, split if >1500, merge if <500
- Produce the decomposition — structured JSON with task ID, file assignments, dependencies, and estimated complexity
Output Format
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.
- 1mo ago First seen · 72 lines · 43 tokens per session scan A c02cae30cfa4
delegation-coordinator is an agent published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 15d ago), licensed MIT. It adds 43 tokens to every session and 837 once invoked, about $0.0002 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 2026-09-03.
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.