claude-code-best-practice is a repository of agents, commands, skills, hooks, plugins, and configuration guidance for Claude Code. It helps developers organize repeatable workflows and apply agentic engineering practices, including in monorepos. The catalogue entries are its reusable Claude Code workflow components.
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/shanraisshan/claude-code-best-practice/researchgit clone --depth 1 https://github.com/shanraisshan/claude-code-best-practiceWrote 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/shanraisshan/claude-code-best-practice/research)<a href="https://agentmods.dev/commands/shanraisshan/claude-code-best-practice/research"><img src="https://agentmods.dev/badge/commands/shanraisshan/claude-code-best-practice/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 | $0.00013 | $0.02858 |
| Opus 5 | $0.00006 | $0.01429 |
| Sonnet 5 | $0.00003 | $0.00572 |
| Haiku 4.5 | $0.00001 | $0.00286 |
Grade A, and why
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- research — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
You MUST parse the user input to extract the feature slug (the folder name in rpi/).
Expected Input Format: rpi/{feature-slug}/REQUEST.md
Purpose
This command performs comprehensive research and analysis of feature requests before the planning phase begins. It acts as a critical GO/NO-GO gate to determine whether a feature idea should proceed to detailed planning.
Key Objectives:
- Assess product-market fit and user value
- Evaluate technical feasibility and complexity
- Identify risks and potential blockers
- Determine the right approach (build, buy, partner, or decline)
- Make go/no-go recommendation with clear rationale
Prerequisites:
- Feature folder exists at
rpi/{feature-slug}/ - Feature request file exists at
rpi/{feature-slug}/REQUEST.md
Output Location: rpi/{feature-slug}/research/RESEARCH.md
This is Step 2 of the RPI Workflow (after initial feature description in Step 1).
Outline
- Load Context: Read feature description from
rpi/{feature-slug}/and project constitution (if exists) - Parse Feature Request: Use requirement-parser agent to extract structured requirements
- Execute Multi-Phase Research:
- Phase 1: Parse Feature Request (requirement-parser agent)
- Phase 2: Product Analysis with Constitution Alignment (product-manager agent)
- Phase 2.5: Technical Discovery (Explore agent) - CRITICAL: Deep code exploration
- Phase 3: Technical Feasibility (senior-software-engineer agent)
- Phase 4: Strategic Assessment (technical-cto-advisor agent)
- Phase 5: Generate Research Report (documentation-analyst-writer agent)
- Synthesize Recommendation: Combine all analyses into clear go/no-go recommendation
- Validate Output: Check against quality gates
- Report Completion: Provide recommendation, next steps, and report location
Phases
Phase 0: Load Context
Prerequisites: Feature slug provided, rpi/{feature-slug}/REQUEST.md exists
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 · 382 lines · 13 tokens per session scan A a29b403477d4
research is a command published in the GitHub repository shanraisshan/claude-code-best-practice (65,631 stars, last pushed today), licensed MIT. It adds 13 tokens to every session and 2,858 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 commands, from other repositories
README
Git workflow and quality assurance commands for the claude-skills repository.
plan-feature
Plan a feature from BRD-lite brief or clear intent into PRD (What), decisions, implementation plan, and task slices.
version
Display current guide and Claude Code versions.
security
This command was migrated to a skill in Claude Code 2.1.3. See: examples/skills/security/SKILL.md.
ccboard-web
Launch ccboard web interface.
ox-session-pause
belongs in the ox CLI JSON output (guidance field), not here. Skills are agent-specific wrappers; ox serves all agents (Codex, etc.). --> Suspend the current session recording. Local cache continues to receive entries, but the upload at stop time will exclude the suspended range.