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-codegit 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 | $0.00027 | $0.01951 |
| Opus 5 | $0.00014 | $0.00975 |
| Sonnet 5 | $0.00005 | $0.00390 |
| Haiku 4.5 | $0.00003 | $0.00195 |
Grade A, and why
slashforge-code 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/slashforge:code
/slashforge:code -quick
/slashforge:code [file]
The full development workflow, from an idea to a merged PR. ==Ten phases, run in order, with four points where it stops and waits for you.==
Argument
The argument is optional. Pass a description, a file, or nothing:
/slashforge:code
/slashforge:code investigation-2026-08-02-1432.html
/slashforge:code docs/spec.md
==If the argument resolves to a file, it is read as the requirements document== and the usual "what do you want to build?" question is skipped — the document already answered it. Anything else is treated as a free-form description, and no argument at all means it asks.
The main source of those files is
/slashforge:investigate, which
ends by printing exactly this command with its report filename filled in.
Pasting it carries the root cause into a fresh session rather than making you
restate the bug from memory.
==Resolution is deliberately forgiving.== A bare filename resolves against
docs/slashforge/investigations/, which is the short form the investigate hand-off prints. A
full path works as given, so docs/spec.md or any other requirements
document is equally valid. A leading @ or # is stripped first, so a pasted
mention still works.
:::note ==A requirements document is an input, not an approval.== Phase 1 still classifies the task, Phase 2 still writes a plan, and the Phase 3 gate still waits for your yes. A report's "suggested next step" is a proposal. :::
The gates
==These are the point of the command. It will not proceed past any of them without your answer:==
| Phase | Gate |
|---|---|
| 3 | Plan confirmation |
| 4 | Branch decision — same branch, or new one plus base and name |
| 8 | PR target branch and reviewers |
| 10 | Branch cleanup after merge |
The phases
| # | Phase | What happens |
|---|---|---|
| 1 | Intake | Requirements gathering; auto-classifies trivial vs full |
| 2 | Plan | Structured plan — changes, surface, env vars, breaking changes, risks, tests |
| 3 | Confirm | You approve the plan |
| 4 | Branch | You choose the branch strategy |
| 5 | Implement | TDD, systematic debugging, or subagent-driven as appropriate |
| 6 | Verify | Lint, tests, build — all must pass |
| 7 | Review | code-reviewer agent pass |
| 8 | Push + PR | You confirm target and reviewers |
| 9 | PR feedback | Handles reviewer comments |
| 10 | Cleanup | You approve branch deletion |
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 · 197 lines · 27 tokens per session scan A d535c34b2be6
slashforge-code is a command published in the GitHub repository rajdeepratan/SlashForge (5 stars, last pushed 6d ago), licensed MIT. It adds 27 tokens to every session and 1,951 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.