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/add)<a href="https://agentmods.dev/commands/hassaan146/forge-mentor/add"><img src="https://agentmods.dev/badge/commands/hassaan146/forge-mentor/add.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 | $0.00019 | $0.00722 |
| Opus 5 | $0.00010 | $0.00361 |
| Sonnet 5 | $0.00004 | $0.00144 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
add 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 8d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/forge:add
For a project that already works. The user says what they want to add, in their own words, and this is the path that gets it built without disturbing what is there.
If this project has no .claude/forge/ yet, stop and tell them to run /forge:start. There
is nothing to add to.
Step 1: read before asking
Call plan_feature with their description. It returns three things:
built_on: the recorded decisions this feature has to live inside, as ids and one-line choices.clashes: anything the feature wants that the project has already ruled out, each naming the decision that would have to be reopened.still_to_ask: the subject questions this feature owes that are not answered yet.
The foundation is not asked again. It is on disk, it is still true, and asking a user a question they have already answered is the fastest way to lose their trust in the record. It is also most of the cost: re-running an interrogation to add one feature spends the tokens of a new project to learn what was already written down.
Say what it is being built on in one line, not a recital. "This lands on top of decision 016, SQLite in one file, and 019, migrations in the repository." They wrote those answers; they need reminding, not re-teaching.
Step 2: put the clashes first
A clash is not a detail to work around. It means the feature, as described, contradicts something the user decided, and there are exactly two honest ways forward:
- Change the feature so it fits what is recorded.
- Change the decision, which is a new decision naming the old one with
supersedes, and a new record saying what changed and why. Never an edit of the old one: the earlier record stays readable and stays in the chain, because the history is what makes any of this auditable.
Put both to the user with render_decision and let them choose. Do not pick for them, and do
not build around a clash quietly, which is the one outcome that leaves a project nobody can
explain.
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.
- 8d ago First seen · 67 lines · 19 tokens per session scan A 8e8c61460eca
add is a command published in the GitHub repository Hassaan146/forge-mentor (22 stars, last pushed 22d ago), licensed MIT. It adds 19 tokens to every session and 722 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.