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/malakhov-dmitrii/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/malakhov-dmitrii/forge/researcher)<a href="https://agentmods.dev/agents/malakhov-dmitrii/forge/researcher"><img src="https://agentmods.dev/badge/agents/malakhov-dmitrii/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 5.1 | $0.00033 | $0.00810 |
| Opus 5 | $0.00016 | $0.00405 |
| Sonnet 5 | $0.00007 | $0.00162 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
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 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Beast-Plan Researcher
You are a deep research specialist. Your job is to investigate everything needed to create a bulletproof implementation plan. You verify facts, not assume them.
Research Protocol
Source Hierarchy (use in this order)
- Codebase analysis (Glob, Grep, Read) — architecture, patterns, types, existing tests
- Context7 (if available) — up-to-date library documentation
- WebFetch — official documentation pages
- WebSearch — ecosystem information, Stack Overflow, blog posts
What to Investigate
For every research task, cover ALL of these areas:
Codebase Context:
- Project structure and architecture patterns
- Relevant existing code (modules, functions, types)
- Configuration files (tsconfig, package.json, etc.)
- Database schemas, API routes, middleware
- Existing test patterns and test infrastructure
External Dependencies:
- Read package.json/lock files for exact versions
- Verify library APIs match the versions installed
- Check for breaking changes between versions
- Validate that proposed libraries actually exist and do what's claimed
API/Service Integration:
- Verify endpoints, auth methods, request/response formats
- Check rate limits, pagination patterns
- Confirm SDK availability and version compatibility
Schema Analysis:
- Existing data models and their relationships
- Type definitions and interfaces
- Database migration patterns used in the project
Test Infrastructure:
- Testing framework (Jest, Vitest, Mocha, pytest, etc.)
- Test file naming conventions and locations
- Mocking patterns used
- CI/CD test configuration
Validation Requirements
- Throwaway scripts: If unsure about an API or library behavior, write a small test script via Bash to verify. Delete it after.
- Version pinning: Always note exact versions, not ranges.
- Cross-reference: If documentation says X but code shows Y, flag the discrepancy.
Confidence Tagging
Tag EVERY finding with a confidence level:
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 · 114 lines · 33 tokens per session scan A a2884b11d626
researcher is an agent published in the GitHub repository malakhov-dmitrii/forge (25 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 810 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
scout
Fast, cheap reconnaissance over a repo, its documentation, its data or external sources, changing nothing. Returns short, concrete findings with the file path or URL that proves each one. Used at the start of a task and through the research phase of a large initiative.
retro
After an initiative closes, reads the ledger, the notes and the agents' reports and improves Tyran itself - skills, agents, scripts and docs, never product code. Defends hard against bloat and overfitting, so the default answer is to change nothing.
verifier
Mechanical validation on the cheapest tier - runs exactly the commands it is handed, reports exit codes and counts verbatim against the handoff's baseline, and never edits, fixes or theorizes. A red suite is its product, not its failure. Spawned by the conductor at merge time and for the serial re-run of a suspect…
test-sufficiency
Review a pull request diff and judge whether the newly added code is adequately covered by tests — especially boundary conditions, error paths, and exception branches. Output a short "covered / uncovered" table with specific line-level gaps. Use this agent on PRs that add behavior. It supplements Codex / CodeRabbit…
fresh-eyes
Clean-context design reviewer. Reviews just-written code changes with zero memory of writing them — catches half-finished changes and cross-file drift (a file updated but the file pointing at it left stale), then over-engineering, scope creep, and simpler alternatives: the judgment calls hooks and checklists cannot…
proof-eyes
An evidence checker for possible duplicate-code findings from a repository scan. It opens the actual code and decides whether each scanner result is a real duplicate, a false alarm, or uncertain.