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/mode)<a href="https://agentmods.dev/commands/hassaan146/forge-mentor/mode"><img src="https://agentmods.dev/badge/commands/hassaan146/forge-mentor/mode.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 | $0.00017 | $0.00497 |
| Opus 5 | $0.00009 | $0.00249 |
| Sonnet 5 | $0.00003 | $0.00099 |
| Haiku 4.5 | $0.00002 | $0.00050 |
Grade A, and why
mode 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.
What it actually says
Change the working mode for this project, or show the current one if no mode was given.
The three differ in exactly one thing — how much gets decided for you (decision 030):
- pipeline — asks about every decision that matters, and confirms each file before writing it
- accept-edits — asks the same questions, and writes without stopping to confirm
- auto — settles small things itself and records them; still asks about anything the rest of the work gets built on
What does not change: code can never move past a question that has not been answered, and the explain-back gate still runs. A mode that turned those off would not be a faster Forge — it would be plain Claude Code with a banner.
Requested mode: $1
Steps:
- Call
next_stepto read where the project currently stands. - If
$1is empty, print the current mode and what it means throughrender_note, then ask which of the three they want throughrender_actionwithkind: "choose"— and stop there. A list of three modes with no framed ask is a paragraph, and the user is left to work out that a reply is expected. - Otherwise call
set_modewith it. - Confirm the change in one line, using the plain-language meaning rather than the mode's name (rule R1 — the name tells a non-technical user nothing).
- If the new mode is
auto, say plainly what Forge will now settle without asking, and what it will still stop for.
In auto mode, every settled choice goes through settle_small_decision. That is the whole
mechanism: it writes the choice, what was picked, and that Forge picked it rather than the
user. Settling something and moving on without it produces a project whose history says a
human made a decision nobody remembers making, which is worse than not recording it at all
(decision 030 accepts records nobody chose, on the condition that the two are never confused
when read back). Load-bearing decisions still go to the user through render_decision in
every mode.
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 · 41 lines · 17 tokens per session scan A 86bca3d4a2e5
mode is a command published in the GitHub repository Hassaan146/forge-mentor (22 stars, last pushed 21d ago), licensed MIT. It adds 17 tokens to every session and 497 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
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.
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.