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 skills/bengous/claude-code-plugins/structured-plannpx skills add bengous/claude-code-plugins --skill structured-plangit clone --depth 1 https://github.com/bengous/claude-code-pluginsWhat 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 | $0.00088 | $0.01052 |
| Opus 5 | $0.00044 | $0.00526 |
| Sonnet 5 | $0.00018 | $0.00210 |
| Haiku 4.5 | $0.00009 | $0.00105 |
Grade A, and why
structured-plan 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 yesterday.
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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Structured Plan
A checklist-driven planning workflow that ensures plans are research-validated, broken into atomic tasks, complete, and self-verifying.
Workflow Overview
Phase A: Clarification (if needed)
↓
Phase B: Iterative Refinement (7 steps)
↓
Exit Plan Mode → Implementation
Phase A: Clarification
If the user's prompt is vague or ambiguous, use AskUserQuestion to clarify before proceeding. Ask about:
- Scope boundaries (what's in/out)
- Technology choices (if multiple options exist)
- Acceptance criteria (how to know it's done)
Once intent is clear, proceed to Phase B.
Phase B: Iterative Refinement
After drafting an initial plan, apply this checklist. Edit the plan file after each step (not one-shot).
Step 1: Research Validation
Validate your approach against official documentation.
- Use WebSearch for patterns, best practices, common gotchas
- Use Context7 for framework/library docs
- If not loaded:
mcp-add context7(lean mode) or skip to WebSearch
- If not loaded:
- Add Best Practices References section to plan with links
## Best Practices References
- [Pattern name](url) - key insight
- [Library docs](url) - relevant section
→ Edit plan file
Step 2: Task Breakdown
Break the plan into atomic, committable tasks.
- Create numbered tasks (Task 1, Task 2, ...)
- Each task must have: Files, Verify, Commit
- Use TaskCreate/TaskUpdate tools to track progress during implementation
See references/task-template.md for format.
→ Edit plan file
Step 3: Task Dependencies
Define execution order with a dependency diagram.
- Use
→for sequential dependencies - Use commas for parallel tasks
- Make dependencies explicit, not implicit
Task 1 → Task 2 → Task 3
Task 4, Task 5 (parallel, after Task 3)
→ Edit plan file
Step 4: Shared Infrastructure
Identify code that would be duplicated across tasks and define shared locations.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 168 lines · 88 tokens per session scan A b24b97e9e3aa
structured-plan is a skill published in the GitHub repository bengous/claude-code-plugins (4 stars, last pushed 2d ago), licensed MIT. It adds 88 tokens to every session and 1,052 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
sql-reporting
Conventions and review steps for writing analytics SQL against the warehouse. Use whenever the task involves querying tables, building a report, or aggregating metrics.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
verify-security
安全校验关卡。自动扫描代码安全漏洞,检测危险模式,确保安全决策有文档记录。当用户提到安全扫描、漏洞检测、安全审计、代码安全、OWASP、注入检测、敏感信息泄露时使用。在新建模块、安全相关变更、攻防任务、重构完成时自动触发。.
development
开发语言能力索引。Python、Go、Rust、TypeScript、Java、C++、Shell。当用户提到编程、开发、代码、语言时路由到此。.
post-build-flow
Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.
n8n:human-like-code-review
Reviews a GitHub pull request like a thoughtful human reviewer and writes the feedback to a markdown file. Prioritizes context, architecture fit, solution complexity, bugs, security edge cases, and missing tests. Use when given a PR URL to review, or when the user says /human-like-code-review.