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 skills add lubochka/xiigen-general-skills --skill stale-baseline-guardgit clone --depth 1 https://github.com/lubochka/xiigen-general-skillsWrote 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/lubochka/xiigen-general-skills/stale-baseline-guard)<a href="https://agentmods.dev/skills/lubochka/xiigen-general-skills/stale-baseline-guard"><img src="https://agentmods.dev/badge/skills/lubochka/xiigen-general-skills/stale-baseline-guard/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/lubochka/xiigen-general-skills/stale-baseline-guard"><img src="https://agentmods.dev/badge/skills/lubochka/xiigen-general-skills/stale-baseline-guard.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00027 | $0.00173 |
| Opus 5 | $0.00014 | $0.00086 |
| Sonnet 5 | $0.00005 | $0.00035 |
| Haiku 4.5 | $0.00003 | $0.00017 |
Grade A, and why
stale-baseline-guard 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 12d 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.
What it actually says
Stale Baseline Guard
Purpose
Avoid acting on outdated context.
When to Use
Use after interruptions, long sessions, branch changes, or concurrent edits.
Inputs
Current files, branch status, latest plan, previous assumptions.
Steps
- Re-read the relevant current state.
- Compare it with the last known state.
- Identify stale assumptions.
- Update the plan before execution.
Gates
Baseline is current or the risk is stated.
Evidence
Fresh file reads, status checks, or updated notes.
Anti-Patterns
Continuing an old plan after files changed.
Related
project-rules-first, claim-verification
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.
- 12d ago First seen · 34 lines · 27 tokens per session scan A 89c4218be850
stale-baseline-guard is a skill published in the GitHub repository lubochka/xiigen-general-skills (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 173 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 2026-08-31.
Other skills, from other repositories
recap
Re-orient inside a long session — produce a dense five-slot status (goal, done, current step, open items, next step) written in the language of the session, plus an optional drill-down into any single item. Reads only what is already in context plus one git call, and never explores the codebase. Use when the user asks…
aidex-comm
Use when the user wants to log or draft a real communication with a person — capture an email/WhatsApp that was received, log a meeting or call that happened, or draft a message/email to send — as a written .context/communications/ entry, kept in the communication's native language. Fires on "log this email", "save…
reset-permissions
Reset accumulated permissions in .claude/settings.local.json. Use when the user says "/reset-permissions" or asks to clear, reset, or clean up Claude Code permissions. Supports full reset (default) or selective reset keeping read-only permissions (--keep-read).
raycast-automator
Use when the user asks to automate a task with Raycast, build a Raycast extension, create a Raycast script command, or mentions Raycast in the context of building something. Triggers on: "automate X with Raycast", "build a Raycast extension", "create a raycast script", "make a raycast command", or any task where…
file-organizer
Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.
weekly
A tool for turning Tracework work logs into workplace-facing weekly reports. Tracework records work across projects, and the report can cover work, personal, or private entries.