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 commands/rajdeepratan/slashforge/slashforge-setupgit clone --depth 1 https://github.com/rajdeepratan/SlashForgeWhat 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 | $0.00023 | $0.00899 |
| Opus 5 | $0.00012 | $0.00449 |
| Sonnet 5 | $0.00005 | $0.00180 |
| Haiku 4.5 | $0.00002 | $0.00090 |
Grade A, and why
slashforge-setup 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 2d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/slashforge:setup
One-time setup for a repository. Explores the codebase, asks clarifying
questions, then ==generates a .claude/ configuration tailored to what it found==.
Handles both fresh repos and partial setups — ==if .claude/ already exists, it
fills gaps rather than overwriting==.
What it creates
| Output | Purpose |
|---|---|
CLAUDE.md |
Root instructions — architecture, conventions, intent routing |
.claude/rules/ |
Conventions the agent must follow |
.claude/skills/ |
Repo-specific procedures |
.claude/agents/ |
Specialist agents, plus shared git and code-reviewer |
.claude/commands/ |
Repo-specific commands |
.claude/hooks/ |
Automated behaviours |
In a monorepo it creates shared rules and root CLAUDE.md, then app-specific
rules, skills, agents, and per-app CLAUDE.md files.
Safe re-runs
Every generated file carries a generated_by marker — YAML frontmatter for
.claude/ files, an HTML comment for CLAUDE.md. On re-run the marker decides
what happens:
| Marker state | Behaviour |
|---|---|
| Present, version current | Safe to refresh |
| Present, version older | Stale — proposes a refresh, asks before overwriting |
| Missing or edited | Treated as yours — gaps filled, never overwritten |
==Remove or edit the marker on any file you want left alone permanently.==
Monorepos
In a monorepo it creates a root CLAUDE.md with shared rules and global agents,
then a separate CLAUDE.md per app with app-specific rules, skills, and
specialist agents.
Graphify
During exploration, /slashforge:setup checks language fit for
Graphify. If at least 70% of
non-trivial source files are in a supported language, it offers to install and
index. On YAML, shell, or config-only repos it skips silently.
This is a setup-time offer, not a per-command check. ==It always shows you the exact commands before asking — nothing is installed without your say-so.==
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.
- 2d ago First seen · 94 lines · 23 tokens per session scan A a3c6111fc5df
slashforge-setup is a command published in the GitHub repository rajdeepratan/SlashForge (5 stars, last pushed 6d ago), licensed MIT. It adds 23 tokens to every session and 899 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 2026-08-31.
Other commands, from other repositories
idea
想法到产品端到端教练 — 一句话想法走到 PRD + 可点击 HTML 原型（会顶嘴、强制砍功能）.
simplify
The over-engineering review: five tags (delete, stdlib, native, yagni, shrink), a mandatory replacement per finding, and a real null result when there is nothing to cut.
research-verify
Verify existing research findings against independent primary sources. Upgrades confidence from 'sources agree' to 'independently verified.'.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
init
Install the formatters this repository needs, with every command visible before it runs.
setup
Fetch Kobiton credentials from the authenticated MCP server and write them to /.kobiton/.credentials.