Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Hassaan146/forge-mentor/plugin install forgeWrote 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/commands/hassaan146/forge-mentor/update)<a href="https://agentmods.dev/commands/hassaan146/forge-mentor/update"><img src="https://agentmods.dev/badge/commands/hassaan146/forge-mentor/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 | $0.00014 | $0.00855 |
| Opus 5 | $0.00007 | $0.00428 |
| Sonnet 5 | $0.00003 | $0.00171 |
| Haiku 4.5 | $0.00001 | $0.00085 |
Grade A, and why
update scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/forge:update
Ask whether this copy of Forge is current, and say what to run if it is not.
Forge checks this once a day on its own and tells you when something is out. This command is for when you want to ask now — usually right after someone has pushed a fix you are waiting on.
Run it
python "${CLAUDE_PLUGIN_ROOT}/scripts/forge_update.py" --force
--force skips the once-a-day cache. Without it you would get this morning's
answer to a question you are asking because something changed this afternoon.
Print whatever it returns, exactly as it comes. Silence means you are current — say so in one line rather than inventing a block, and do not describe the check itself. Nobody asked how it works.
Two different answers, and they are not interchangeable
"An update is out." A newer version exists on GitHub and is not on this machine. Ask, then run it yourself. Do not hand the user two commands to type: they have Claude Code open, you have a shell, and the whole point of the notice is to save them the trip.
On yes, run both, in this order, because the second reads the local catalogue and the first is what refreshes it. Run the second alone and it finds nothing, reports success, and changes nothing, which is the loop this exists to end:
claude plugin marketplace update forge-marketplace
claude plugin update forge@forge-marketplace
Then say the version that landed and that a restart is what loads it. On no, say "fine, it will keep" in one line and carry on. Do not ask twice in a session, and never update without being told to: swapping the tool underneath a session that is mid-decision is how you get half of one version and half of another.
"It is downloaded, this session is running the old one." The update already worked. Nothing needs downloading again, and running the update command a second time will report success and change nothing, which is the loop that wastes an afternoon. What is left is one restart.
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.
- 7d ago First seen · 86 lines · 14 tokens per session scan A 1e0c9c9a98d6
update is a command published in the GitHub repository Hassaan146/forge-mentor (22 stars, last pushed 21d ago), licensed MIT. It adds 14 tokens to every session and 855 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 2026-08-30.
Other commands, from other repositories
park
Park current session for later resume (append to Markdown file).
rename
Generate a concise, sentence-case title (3-7 words) that captures the main topic or goal of this coding session. The title should be clear enough that the user recognizes the session in a list. Use sentence case: capitalize only the first word and proper nouns.
audit-agents-skills
Audit quality of agents, skills, and commands in a Claude Code project.
security-audit
Comprehensive security audit of your project AND Claude Code configuration. Analyzes secrets exposure, injection surfaces, dependencies, hook security, and produces a scored security posture assessment.
audit-quiz-coverage
Find quiz coverage gaps from recent guide/CHANGELOG/CC-releases changes and propose new questions.
worktree
Create a git worktree for isolated feature/fix work.