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/flagrare/llm-tutor/tutor-updatenpx skills add Flagrare/llm-tutor --skill tutor-updategit clone --depth 1 https://github.com/Flagrare/llm-tutorWrote 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/flagrare/llm-tutor/tutor-update)<a href="https://agentmods.dev/skills/flagrare/llm-tutor/tutor-update"><img src="https://agentmods.dev/badge/skills/flagrare/llm-tutor/tutor-update.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 | $0.00069 | $0.00605 |
| Opus 5 | $0.00034 | $0.00302 |
| Sonnet 5 | $0.00014 | $0.00121 |
| Haiku 4.5 | $0.00007 | $0.00060 |
Grade A, and why
tutor-update scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tutor Update
This skill answers the question "is there a newer version of llm-tutor than the one I'm running, and what would I get by upgrading?" It compares the installed plugin-cache version against the latest GitHub release, prints the release notes when an upgrade is available, and provides the two exact slash commands the user needs to type to perform the upgrade.
llm-tutor is a Claude Code plugin, so its install/update lifecycle is owned by /plugin update llm-tutor@llm-tutor + /reload-plugins. A skill cannot invoke another slash command, so this skill stops short of performing the update itself. What it does instead is the version check + diff that makes the manual upgrade worth doing — and tells you when you can skip it.
Step 1 — Run the check script
bash "$CLAUDE_PLUGIN_ROOT/scripts/check-for-update.sh"
Echo the script's output verbatim. Don't summarize — the user wants to see the installed version, the latest version, and (when behind) the actual release notes.
Step 2 — Add a one-line context line
If the script reports "You're up to date," no further action is needed. Optionally note the current version.
If the script reports "Update available!", the script already prints the two commands. Add a single line of context:
"Run those two commands above to upgrade — the second one (
/reload-plugins) is required for the new version to take effect in the current Claude Code session without a restart."
If the script reports "(couldn't reach GitHub)", suggest the user check their network and try again, or visit the releases page directly.
Hard rules
- Never invoke
/plugin updatefrom this skill. It's a Claude Code built-in slash command and skills can't trigger other slash commands. The user has to type it themselves. - Never edit
~/.claude/plugins/cache/llm-tutor/directly to "force" an update. That bypasses Claude Code's plugin registry (~/.claude/plugins/installed_plugins.json) and leaves the install in an inconsistent state. The lifecycle is owned by/plugin update. - Don't run if the user is mid-tutoring-session and has unsaved progress. Tutoring state is in
state.jsonand survives updates — but a reload mid-conversation may discard the active turn's context. Mention this if the user has an activein_progresstopic and is mid-dialogue.
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.
- 5d ago First seen · 41 lines · 69 tokens per session scan A 37b469f92866
tutor-update is a skill published in the GitHub repository Flagrare/llm-tutor (5 stars, last pushed 3mo ago), licensed MIT. It adds 69 tokens to every session and 605 once invoked, about $0.0003 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
chief-strategy-officer
Owns where the business plays and how it wins over a multi-year horizon — portfolio choices, corporate development, strategic partnerships, and planning under uncertainty. Use this for a decision about which markets or businesses to be in, whether to build, buy, or partner, how to allocate capital across business…
seo-strategy
Audits and improves organic search performance — technical health, site architecture, internal linking, structured data, and the content decisions that determine what can rank. Use this to run an SEO audit, diagnose why pages are not ranking or were deindexed, plan a site's URL and navigation structure, add structured…
financial-statement-analysis
Reads a set of financial statements and establishes what changed and why — fluctuation analysis against prior period and against budget, profitability, liquidity, solvency and efficiency ratios, benchmarking, and the non-GAAP measures presented alongside them. Use this to interpret results, review a counterparty's or…
youtube-producer
Plans, packages, and scripts long-form video for retention and channel growth — idea selection, titles and thumbnails, script structure, and diagnosing why a video or channel underperforms. Use this for video ideas, packaging, scripting, a retention teardown, or channel strategy — including when someone describes a…
estimating-and-contingency
Produces a cost or effort estimate someone can defend — decomposing the work, choosing between analogous, parametric and bottom-up methods, documenting the basis and its assumptions, expressing confidence as a range, and sizing contingency and management reserve separately. Use this to build an estimate, challenge one…
scenario-planning
Plans under genuine uncertainty — building scenarios, identifying which assumptions are load-bearing, setting early-warning indicators, and stress-testing a plan against futures rather than forecasting one. Use this when a decision depends on something unknowable, when a plan assumes conditions that may not hold…