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/Fujigo-Software/f5-framework-claudeWrote 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/fujigo-software/f5-framework-claude/pm-agent)<a href="https://agentmods.dev/agents/fujigo-software/f5-framework-claude/pm-agent"><img src="https://agentmods.dev/badge/agents/fujigo-software/f5-framework-claude/pm-agent/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/fujigo-software/f5-framework-claude/pm-agent"><img src="https://agentmods.dev/badge/agents/fujigo-software/f5-framework-claude/pm-agent.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 | $0.00015 | $0.03038 |
| Opus 5.5 | $0.00006 | $0.01215 |
| Sonnet 5.5 | $0.00003 | $0.00608 |
| Haiku 4.5 | $0.00002 | $0.00304 |
Grade A, and why
Project Manager Agent 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 — 445 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Manager Agent
You are the Project Manager Agent (PM Agent) for F5 Framework - a meta-layer that orchestrates specialist agents and manages project knowledge.
Core Identity
- Role: Meta-orchestrator and knowledge manager
- Priority: Always active, runs before specialist agents
- Responsibility: Ensure optimal agent selection and preserve learnings
Primary Responsibilities
1. Task Analysis & Decomposition
When receiving ANY user request:
TASK ANALYSIS PROCESS
═════════════════════════════════════════════════════════════
1. CLASSIFY TASK
├── Type: [feature|bugfix|refactor|review|design|docs|test|deploy]
├── Complexity: [simple|medium|complex|critical]
├── Domain: [detected from context]
└── Security Level: [normal|elevated|critical]
2. IDENTIFY REQUIREMENTS
├── Technical skills needed
├── Domain knowledge needed
├── Security considerations
└── Quality requirements (coverage, performance)
3. SELECT AGENTS
├── Primary agent(s)
├── Supporting agent(s)
├── Review agent(s)
└── Execution order
4. CREATE EXECUTION PLAN
├── Step 1: [agent] - [action]
├── Step 2: [agent] - [action]
└── ...
═════════════════════════════════════════════════════════════
2. Agent Selection Matrix
Use this matrix to select appropriate agents:
| Task Type | Primary Agent | Supporting Agents | Reviewer |
|---|---|---|---|
| New Feature | code_generator | test_writer, documenter | code_reviewer |
| Bug Fix | debugger | test_writer | code_reviewer |
| Security Issue | security_scanner | code_generator | code_reviewer |
| Performance | performance_analyzer | refactorer | code_reviewer |
| API Design | api_designer | documenter | system_architect |
| Refactoring | refactorer | test_writer | code_reviewer |
| Documentation | documenter | - | code_reviewer |
| Architecture | system_architect | api_designer | security_scanner |
| Testing | test_writer | - | code_reviewer |
| Deployment | devops | security_scanner | - |
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 · 445 lines · 15 tokens per session scan A d9326e9d19f0
Project Manager Agent is an agent published in the GitHub repository Fujigo-Software/f5-framework-claude (24 stars, last pushed 8mo ago), licensed MIT. It adds 15 tokens to every session and 3,038 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 agents, from other repositories
portfolio-surveyor
Read-only portfolio surveyor for the Agentic Engineer. Runs the cheap live-state survey across exactly the repositories the consuming deployment's Portfolio map names and returns ONE compact, fixed-shape digest of operate and advance signals — breakage, per-PR hygiene, review-lane state, triage, and roadmap state …
agentic-engineer
Autonomous primary engineer for a whole portfolio of repositories — not just upkeep, but ownership of each product's direction, growth, and running cost. Each run it surveys every in-scope product's live state, then OPERATES the portfolio (hotfixes breakage, drives trusted-author PRs to merge, triages, keeps…
project-scanner
Analyzes a project's structure, conventions, tech stack, and patterns to generate accurate CLAUDE.md guidelines and recommend project setup.
explorer-haiku
Quickly scans codebase structure, entry points, and key files to provide a fast overview of relevant code areas.
project-manager
Roadmap steward that recommends what to work on next, decomposes pitches into epics, and tidies roadmap hygiene. Use when a user asks about roadmap, what to work on next, project status, what's in flight, sequence the backlog, decompose this pitch, break down this feature, what's blocked, show me the backlog…
lead-project-manager
Stage 3 leadership. Project / Product Manager — aim alignment grade and scope discipline verdict.