Borrowing it
Nothing to install: this file belongs to dlupiak/claude-session-dashboard. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dlupiak/claude-session-dashboard/main/.claude/skills/feature/SKILL.mdgit 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/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/skills/dlupiak/claude-session-dashboard/feature"><img src="https://agentmods.dev/badge/skills/dlupiak/claude-session-dashboard/feature.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 99 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Rogue Agent · line 127 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 5.5 | $0.00050 | $0.01006 |
| Sonnet 5.5 | $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 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 — 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.
- 1mo 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 (76 stars, last pushed 3d ago), licensed MIT. It adds 126 tokens to every session and 2,516 once invoked, about $0.0005 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 2026-09-01.
Other skills, from other repositories
example-feature-generator
Generate boilerplate for new features following project conventions. Use when user says "create feature", "add feature", or "new feature scaffolding".
Vizra ADK Memory System
Implement persistent memory, session context, and vector memory (RAG) for AI agents.
authentication-patterns
OAuth 2.0, JWT, SSO, MFA, NextAuth/Clerk/Supabase Auth implementation patterns.
agent-flutter-developer
Specialist subagent: Flutter/Dart cross-platform development, Riverpod state management, and platform channels specialist. Use when building Flutter apps, implementing state management, or working with native platform features. Trigger phrases: Flutter, Dart, Riverpod, Bloc, widget, MaterialApp, GoRouter, platform…
content-repurposer
Adapt content across platforms with tone/format shifting — blog to social, long to short, text to visual outline. Use when repurposing content for different channels, audiences, or formats.
electron-desktop
Desktop application development with Electron for Windows, macOS, and Linux. Use when building cross-platform desktop apps, implementing native OS features, or packaging web apps for desktop.