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.
git clone --depth 1 https://github.com/Hassaan146/forge-mentorWrote 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/stop)<a href="https://agentmods.dev/commands/hassaan146/forge-mentor/stop"><img src="https://agentmods.dev/badge/commands/hassaan146/forge-mentor/stop.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 | $0.00012 | $0.00516 |
| Opus 5 | $0.00006 | $0.00258 |
| Sonnet 5 | $0.00002 | $0.00103 |
| Haiku 4.5 | $0.00001 | $0.00052 |
Grade C, and why
stop scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
git rm -r --cached .claude/forge && rm -rf .claude/forge How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/forge:stop
Stop Forge acting in this project. The gates stop blocking, the questions stop coming, and Claude Code goes back to being ordinary Claude Code here.
Nothing is deleted. Every decision, the chain, the phases and the progress file stay exactly where they are. They are the project's own history and they outlive the tool that produced them, which is the whole point of keeping them in the repository rather than in a session (decision 016).
How
Write .claude/forge/paused.md with the date and, if the user gave one, the
reason. That file existing is the whole mechanism: every hook checks for it
first and stands down.
A file rather than a setting, deliberately. Each hook has to answer "am I on" before it does anything, and a file either exists or it does not: nothing to parse, nothing that can be malformed, and no way for a damaged note to leave somebody locked out of their own repository. It can also be created or deleted by hand, and its presence is obvious in a directory listing.
Then say, in one framed block:
- Forge is off here, and what that means: no gates, no questions, no blocked writes.
- The records are untouched and still committed with the code.
/forge:startturns it back on and picks up where it left off, because the state was never in the session.
If they want it gone entirely
Deleting the notes is theirs to do, not yours. Say the command and let them run it:
git rm -r --cached .claude/forge && rm -rf .claude/forge
Before you show that, say plainly what it costs: every recorded decision, the
reasoning behind it, the options that were turned down and the chain that proves
none of it was edited afterwards. That is the record that answers "why is this
built this way" in six months, and prompts.md and Code Explained are generated
from it. Removing the plugin does not require removing the record.
Never run it yourself, however clearly they ask. This is the one action in Forge that destroys work, and the rule everywhere else in the product is that nothing is destroyed: repair quarantines before it overwrites, and blocked writes are refused rather than discarded.
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 · 54 lines · 12 tokens per session scan C 876280a6f133
stop is a command published in the GitHub repository Hassaan146/forge-mentor (22 stars, last pushed 21d ago), licensed MIT. It adds 12 tokens to every session and 516 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
audit-agents-skills
Audit quality of agents, skills, and commands in a Claude Code project.
audit-whitepapers
Audit version freshness, FR/EN parity, and metadata quality of all whitepapers and recap cards.
audit-repo-docs
Audit repository documentation against 85+ best practices from claude-code-ultimate-guide.
boldguy-linkedin-answer
Draft a LinkedIn comment on a post, referencing the guide's relevant section, in Flow style with AI markers removed.
methodology-advisor
Analyzes your codebase and asks 3 targeted questions to recommend the right AI-assisted development methodology stack.
release
Release guide version (CHANGELOG + VERSION + README + landing sync + commit + push).