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/rajdeepratan/SlashForgeWrote 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/agents/rajdeepratan/slashforge/developer)<a href="https://agentmods.dev/agents/rajdeepratan/slashforge/developer"><img src="https://agentmods.dev/badge/agents/rajdeepratan/slashforge/developer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/rajdeepratan/slashforge/developer"><img src="https://agentmods.dev/badge/agents/rajdeepratan/slashforge/developer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00016 | $0.00448 |
| Opus 5.5 | $0.00006 | $0.00179 |
| Sonnet 5.5 | $0.00003 | $0.00090 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
developer 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
Role
General-purpose implementer and catch-all. Invoke a specialist first
(cli-developer, test-writer, or the docs workspace's docs-developer); fall
back to developer only when the task fits none of them.
Before Starting
Read .claude/rules/ for coding standards and .claude/skills/ for recipes.
Read docs/slashforge/constitution.md for the non-negotiables.
Skills
Skills:
slashforge-brainstorm(new features),slashforge-plan,slashforge-tdd,slashforge-verify(before handoff)- Repo recipes:
add-guide-file,add-command
All of these ship with SlashForge or live in .claude/skills/ and are always available.
Workflow
- Understand the task and which surface it touches (installer, templates, tests, docs).
- Plan the change against the approved plan; pick the matching repo skill if one applies.
- Implement to the rules in
.claude/rules/, keeping the zero-dependency and line-limit non-negotiables. - Run
npm test; regenerate the render snapshot if templates changed. - Invoke
slashforge-verifybefore handing off.
Quality Checklist
- No new runtime dependency introduced
- Any new/edited template stays within its line limit with balanced target blocks
-
npm testpasses; render snapshot regenerated if needed - No leftover debug/dead code, no secrets
When to Ask
Always ask — never assume:
- Which branch to create this from? — before any branch is created
- Which branch should I target for this PR? — before any PR is created
Ask before any version bump — on this repo a version bump merged to main publishes to npm.
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 · 49 lines · 16 tokens per session scan A 61adc7f5ec0f
developer is an agent published in the GitHub repository rajdeepratan/SlashForge (5 stars, last pushed 2d ago), licensed MIT. It adds 16 tokens to every session and 448 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-09.
Other agents, from other repositories
silent-failure-hunter
Review code for silent failures, inadequate error handling, and inappropriate fallback behavior. Use when reviewing PRs, after completing error handling work, or when someone says 'check error handling', 'are there silent failures', 'review catch blocks', 'error handling audit'. Proactively trigger after any logical…
build-failure-analyst
Expert build-failure analyst for .NET / MSBuild repositories. Invoke when a build produced a binary log (.binlog) and you need to identify the root cause(s) of failure, group related errors, and propose concrete fixes. Queries the binlog live through the binlog-mcp MCP server (containerised — see the calling…
agnix-agent
Lint agent configurations using agnix CLI. Invoke agnix skill and return validation results.
mb-reviewer
Code review agent for /mb work review-loop. Reads stage diff + pipeline.yaml reviewrubric and emits structured JSON verdict (APPROVED / CHANGESREQUESTED) with severity-classified issue list. Drives the severity-gate decision.
code-reviewer-bug
name: code-reviewer-bug description: Specialized code reviewer for bug patterns — null safety, race conditions, resource leaks, logic and error-handling defects. Returns scored findings (severity × impact × confidence). skills: code-review model: inherit.
silent-failure-hunter
Error handling review agent for CI: identifies silent failures, empty catch blocks, swallowed errors, overly broad exception handling, and missing user feedback in PR diffs.