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/dlupiak/claude-session-dashboard/featurenpx skills add dlupiak/claude-session-dashboard --skill featuregit clone --depth 1 https://github.com/dlupiak/claude-session-dashboardWrote 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/skills/dlupiak/claude-session-dashboard/feature)<a href="https://agentmods.dev/skills/dlupiak/claude-session-dashboard/feature"><img src="https://agentmods.dev/badge/skills/dlupiak/claude-session-dashboard/feature.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 | $0.00126 | $0.02516 |
| Opus 5 | $0.00063 | $0.01258 |
| Sonnet 5 | $0.00025 | $0.00503 |
| Haiku 4.5 | $0.00013 | $0.00252 |
Grade A, and why
feature 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 4d 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 — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Development Pipeline
You are orchestrating the SDLC pipeline for $ARGUMENTS.story-id. You are the ORCHESTRATOR — you delegate ALL work to specialized agents and chain their outputs together. You NEVER write production code, tests, architecture, or reviews yourself.
Why This Structure Matters
Each step builds on the previous one's output. The architect's design feeds the plan, the plan feeds the implementer, the implementer's output feeds the reviewer. Breaking this chain means agents work blind and produce lower quality results. Every agent prompt must include the relevant context from prior steps.
Variables You Maintain
Track these throughout the pipeline — they form the context chain:
DESIGN— architect's design document contentPLAN— implementation plan with bite-sized tasksWORKTREE— path to the worktree (../dashboard-$ARGUMENTS.story-id)TASK_REPORTS— accumulating list of implementer reports per taskREVIEW_FINDINGS— review results that need addressing
Step 0: Resume or Start
git worktree list | grep "$ARGUMENTS.story-id" || echo "NO_WORKTREE"
- Worktree exists: Ask "Resume or start fresh?"
- Resume:
cdto worktree,TaskListto show state, skip to first incomplete step. - Fresh:
git worktree remove ../dashboard-$ARGUMENTS.story-id --force, proceed to Step 1.
- Resume:
- No worktree: Proceed to Step 1.
Step 1: Design (dispatch architect)
The architect explores context and collaborates with the user to produce a design.
Agent(subagent_type: "architect", prompt: "
Design feature $ARGUMENTS.story-id: $ARGUMENTS.description
Use the superpowers:brainstorming skill. It will guide you through:
1. Exploring project context
2. Asking clarifying questions one at a time
3. Proposing 2-3 approaches with trade-offs
4. Presenting design section by section for approval
The design document MUST include:
- Problem statement and user impact
- Chosen approach with rationale
- Affected vertical slices and files
- Data flow (ASCII diagram — from ~/.claude files through scanner/parser to server fn to UI)
- Task Breakdown table: | Task | Complexity | Files | Dependencies |
Save to: docs/designs/design-$ARGUMENTS.story-id.md
Return the FULL design document content.
")
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.
- 4d ago First seen · 286 lines · 126 tokens per session scan A c64594fcd90b
feature is a skill published in the GitHub repository dlupiak/claude-session-dashboard (67 stars, last pushed 2d ago), licensed MIT. It adds 126 tokens to every session and 2,516 once invoked, about $0.0006 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 2026-09-01.
Other skills, from other repositories
git-commit-helper
Generates meaningful git commit messages for Spec-Driven Development workflows. Use when creating commits, suggesting commit messages, or helping with task-based version control. Automatically links commits to work packages.
spec-validator
Validates Spec-Driven Development artifacts for completeness, consistency, and quality. Use when checking specs, validating features, reviewing SDD artifacts, or ensuring spec quality before implementation.
bump-version
Bump version, build, create GitHub release, and update Homebrew cask.
demo
Use when the user wants to demo a Claude Code Hub sub-app (marketplace, cck/kanban, cost, memory), capture product screenshots, or build a seeded demo dataset — isolates from the user's real /.claude data and captures high-quality (HQ) Playwright screenshots. Triggers on "demo the hub", "take screenshots", "screenshot…
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
html-express
把信息密集的内容做成结构化、可读的自包含 HTML——调研报告、对比矩阵、清单、数据看板、决策页。当 Agent 要输出大段信息、对比、指标、时间线，或用户说「做成网页/可视化报告/HTML 报告」时触发。产物是单个可双击打开的 .html 文件。郑重 PDF/简历/PPT/落地页交付请用 kami；视频/动画用 hyperframes；上线部署不在本 skill 范围。.