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 commands/fujigo-software/f5-framework-claude/f5-researchgit 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/commands/fujigo-software/f5-framework-claude/f5-research)<a href="https://agentmods.dev/commands/fujigo-software/f5-framework-claude/f5-research"><img src="https://agentmods.dev/badge/commands/fujigo-software/f5-framework-claude/f5-research.svg" alt="Measured on agentmods" 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 | $0.00007 | $0.02424 |
| Opus 5 | $0.00003 | $0.01212 |
| Sonnet 5 | $0.00001 | $0.00485 |
| Haiku 4.5 | $0.00001 | $0.00242 |
Grade A, and why
f5-research 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 6d 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.
/f5-research - Deep Research
Conduct deep research with AI agents and multi-source synthesis.
ARGUMENTS
The user's request is: $ARGUMENTS
PURPOSE
Deep research for complex investigations:
- Multi-source information gathering
- Evidence synthesis and validation
- Structured analysis and reporting
- Quality gate D1 (Research Complete) support
RESEARCH CAPABILITIES
| Capability | Description | Tools Used |
|---|---|---|
| Web Search | Current information from web | Tavily |
| Documentation | Official library/framework docs | Context7 |
| Code Analysis | Codebase investigation | Serena, Grep |
| Reasoning | Complex multi-step analysis | Sequential |
| Validation | Cross-reference and verify | Multiple |
ACTIONS
Start Research Session
/f5-research "React Server Components best practices"
Output:
🔍 Starting Deep Research Session
Topic: React Server Components best practices
Planning research strategy...
Research Plan:
1. Search for official React documentation
2. Find community best practices (2024)
3. Identify common patterns and anti-patterns
4. Gather performance considerations
5. Synthesize findings
Estimated sources: 10-15
Estimated time: 2-3 minutes
Beginning research...
Research with Specific Focus
/f5-research "authentication patterns" --focus security
Output:
🔍 Deep Research: Authentication Patterns
Focus Area: Security
Research Plan:
1. Search for OWASP authentication guidelines
2. Find JWT security best practices
3. Research session management patterns
4. Identify common vulnerabilities
5. Gather mitigation strategies
Security-focused sources:
• OWASP guidelines
• CVE databases
• Security advisories
• Penetration testing reports
Beginning security-focused research...
Research for Requirements (Gate D1)
/f5-research "user authentication requirements" --gate D1
Output:
🔍 Requirements Research (Gate D1)
Topic: User Authentication Requirements
Research aligned with Gate D1 criteria:
• Evidence count target: ≥3 sources
• Quality score target: ≥80%
Research Plan:
1. Industry standards review
2. Competitor analysis
3. User expectations research
4. Security requirements
5. Compliance requirements (if applicable)
Progress tracking:
Sources found: 0/3 minimum
Quality score: Calculating...
Beginning D1-focused research...
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.
- 6d ago First seen · 487 lines · 7 tokens per session scan A 87ddabf8628f
f5-research is a command published in the GitHub repository Fujigo-Software/f5-framework-claude (24 stars, last pushed 7mo ago), licensed MIT. It adds 7 tokens to every session and 2,424 once invoked, about $0.0000 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 commands, from other repositories
plan
Project spec (no args) or feature FRD (with args).
debug
Structured debugging with parallel investigation agents.
init
Analyze codebase and generate CLAUDE.md with project conventions.
release
Generate changelog, bump version, and create git tag.
docs
Generate or update project documentation from codebase and specs.
review
Multi-agent code review with parallel validation.