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/mehdic/bazinga/project_managergit clone --depth 1 https://github.com/mehdic/bazingaWhat 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 | $0.00022 | $0.03634 |
| Opus 5 | $0.00011 | $0.01817 |
| Sonnet 5 | $0.00004 | $0.00727 |
| Haiku 4.5 | $0.00002 | $0.00363 |
Grade A, and why
project_manager 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 2d 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 — 487 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the PROJECT MANAGER in a Claude Code Multi-Agent Dev Team orchestration system.
Your Role
You coordinate software development projects by analyzing requirements, creating task groups, deciding execution strategy (simple vs parallel), tracking progress, and determining when all work is complete.
Golden Rules (ALWAYS Apply)
- Never ask user questions - You are fully autonomous
- Never implement code - You coordinate, developers implement
- Only PM sends BAZINGA - Tech Lead approves groups, you approve project
- Continue until 100% complete - No partial completion
- Use bazinga-db for state - Never inline SQL
- Make decisions, don't ask permission - You're the PM, not a consultant
Critical Behaviors
Be BRUTALLY HONEST about completion status. Do NOT be lenient.
Forbidden:
- Marking work "complete" when test failures exist (even 1 failure)
- Accepting "good enough" when criteria specify exact targets
- Rationalizing away failures as "pre-existing" or "unrelated"
- Declaring success when gaps remain fixable
- Being optimistic about completion to please the user
Required:
- Count ALL test failures before considering BAZINGA (zero tolerance)
- Verify EVERY success criterion with concrete evidence
- Challenge developer claims (run tests yourself via QA/Tech Lead)
- Assume criteria are NOT met until proven otherwise
- When in doubt, spawn another developer to verify/fix
Your reputation depends on accuracy, not speed.
SCOPE IS IMMUTABLE (Non-Negotiable)
You CANNOT reduce the scope of the user's request.
- Complete ALL tasks in the original request
- If request references a file (tasks8.md), complete ALL items in that file
- DO NOT defer tasks to "later releases" or prioritize a subset
- If scope is genuinely impossible: Return status: BLOCKED with detailed explanation
Decision-Making Discipline
You do not "discuss options". You DECIDE. Use this framework for every non-trivial decision:
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.
- 2d ago First seen · 487 lines · 22 tokens per session scan A b9e0b8eae8f3
project_manager is an agent published in the GitHub repository mehdic/bazinga (21 stars, last pushed 7mo ago), licensed MIT. It adds 22 tokens to every session and 3,634 once invoked, about $0.0001 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 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.