**Audience:** this skill is for the instar-developing agent (Echo, or any agent assigned instar-dev responsibilities). It is NOT a user-facing skill. End users of instar should never invoke `/instar-dev` and will never see it in their workflow — it runs at the infrastructure-developer layer, not t

**Audience:** the instar-developing agent. End users do not invoke this. Throughout this document, "the agent" refers to the instar-developing agent running the skill.

Without identity infrastructure, every Claude Code session starts from zero. The agent has no name, no remembered preferences, no sense of who it works with or what it has learned. Context compaction erases everything mid-session. This skill fixes that — no external tools required.

Claude Code has no memory between sessions by default. Every conversation starts blank. But a project's knowledge accumulates — commands discovered, patterns debugged, preferences revealed, mistakes made and corrected. Without persistence, that knowledge is lost every time the window closes.

Claude Code runs shell commands, edits files, and manages infrastructure with real consequences. Without guardrails, a misunderstood instruction or a hallucinated flag can delete data, corrupt history, or expose credentials. This skill installs a PreToolUse hook that blocks the most dangerous operat

Instar has a built-in feedback system that routes issues and feature requests directly to the instar maintainers. Your agent is not just using instar — it's part of the ecosystem that improves it. Every bug report, feature request, and observation lifts all ships.

Instar's identity system gives agents a continuous self that survives context compaction, session restarts, and autonomous operation. Identity isn't stored in context — it's stored in infrastructure. Structure over willpower.

Instar's job scheduler lets you define tasks that run automatically on a cron schedule. Each job spawns a real Claude Code session — with full tool access, sub-agents, and context — at the specified interval.

Build a searchable knowledge base from external sources -- URLs, documents, transcripts, PDFs. Uses the existing MemoryIndex (FTS5) for search, so no new dependencies.

Focused micro-skill for secret management setup. Explains options, guides through Bitwarden installation/login/unlock, configures backend. Exits when done.

**Version / slug:** `pr-gate-phase-a-commit-6-rollback-skill` **Date:** `2026-04-17` **Author:** `Echo (instar-developing agent)` **Second-pass reviewer:** `not required — skill registration, inert at rest, no runtime surface until explicitly invoked`

Fetching a webpage with the default WebFetch tool retrieves full HTML — navigation menus, footers, ads, cookie banners, and all. For a documentation page, 90% of the tokens go to chrome, not content. This script fixes that by trying cleaner sources first.

When something breaks, the instinct is to start changing code — adding logs, tweaking values, commenting things out. This is probing, not debugging. Probing works sometimes, but it scales poorly and teaches nothing. Structured debugging finds the root cause, fixes it once, and leaves you understan