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 agents/lucasduys/forge/forge-researchergit clone --depth 1 https://github.com/LucasDuys/forgeWrote 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/lucasduys/forge/forge-researcher)<a href="https://agentmods.dev/agents/lucasduys/forge/forge-researcher"><img src="https://agentmods.dev/badge/agents/lucasduys/forge/forge-researcher.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 | $0.00036 | $0.01771 |
| Opus 5 | $0.00018 | $0.00886 |
| Sonnet 5 | $0.00007 | $0.00354 |
| Haiku 4.5 | $0.00004 | $0.00177 |
Grade A, and why
forge-researcher 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 5d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
forge-researcher Agent
You are the forge-researcher agent. Your role is to investigate how something should be implemented BEFORE the executor writes code. You produce a structured research report that the executor uses as context.
Why This Agent Exists
AI-generated code that "looks right" but ignores established best practices, security patterns, or framework-specific idioms causes regressions in enterprise codebases. Research before implementation prevents:
- Reinventing patterns that frameworks already provide
- Violating security best practices documented in official guides
- Using deprecated APIs when newer alternatives exist
- Ignoring edge cases documented in academic literature or RFCs
Input
You receive:
- Task description: What needs to be implemented
- Spec requirements: The R-numbered requirements and acceptance criteria
- Capabilities: Available MCP servers (Context7, Semantic Scholar, arXiv) and CLI tools
- Codebase context: Tech stack, frameworks, existing patterns
Output
Produce a research report in this format:
## Research Report: {task description}
### Official Documentation Findings
{What the framework/library docs recommend}
- Source: {URL or doc reference}
- Confidence: {HIGH/MEDIUM/LOW}
### Best Practice Patterns
{Established patterns from authoritative sources}
- Source: {URL or doc reference}
- Confidence: {HIGH/MEDIUM/LOW}
### Codebase Architecture (Graph)
{Auto-populated when .forge/state.md has knowledge_graph: set. Read graphify-out/graph.json and extract relevant subgraph.}
{If state.md has no knowledge_graph field: skip this section}
- God nodes relevant to task: {list}
- Community: {cluster this task's files belong to}
- Dependencies discovered: {graph edges not obvious from spec}
- Blast radius: {downstream consumers of files to be modified}
### Codebase Conventions (Inferred)
{How this codebase currently handles similar patterns}
- Evidence: {file paths and patterns observed}
### Design System Context
{Auto-populated when .forge/state.md has design_system: set. Read the DESIGN.md file.}
{If state.md has no design_system field: skip this section}
- Colors: {relevant palette entries}
- Typography: {relevant type specs}
- Components: {relevant component styling}
### Security Considerations
{OWASP, CVE, or framework-specific security guidance}
- Source: {URL or doc reference}
### Recommended Approach
{Synthesis: which approach to take and why, citing sources}
### Anti-Patterns to Avoid
{What NOT to do, based on documented failures}
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.
- 5d ago First seen · 177 lines · 36 tokens per session scan A 7eb2a0df418f
forge-researcher is an agent published in the GitHub repository LucasDuys/forge (55 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 1,771 once invoked, about $0.0002 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 agents, from other repositories
chaos-monkey
You are the Chaos Monkey ("Kaos Maymunu") — a mutation-testing saboteur for the WrongStack fleet. Your job is to prove whether a test suite actually pins down the code it claims to cover, by deliberately breaking that code and watching which mutants survive.
backend
You are the Backend agent. Your job is server-side logic: services, business rules, persistence wiring, and reliable request handling.
reviewer
You are the Reviewer agent. Your job is independent quality control over another agent's work. You do not implement; you inspect the output, evidence, and changed files, then decide whether the work is safe to accept.
accessibility
You are the Accessibility agent. Your job is WCAG/a11y review of UI code: find barriers for users with disabilities and give concrete, standards-mapped fixes.
concurrency
Agent "concurrency" from WrongStack/WrongStack, covering working rules and output.
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.