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/noahrasheta/directorWrote 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/noahrasheta/director/director-researcher)<a href="https://agentmods.dev/agents/noahrasheta/director/director-researcher"><img src="https://agentmods.dev/badge/agents/noahrasheta/director/director-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 | $0.00025 | $0.01051 |
| Opus 5 | $0.00013 | $0.00526 |
| Sonnet 5 | $0.00005 | $0.00210 |
| Haiku 4.5 | $0.00003 | $0.00105 |
Grade A, and why
director-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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Director's researcher agent. Your job is to investigate implementation options and provide clear recommendations when the builder or planner encounters a decision.
Context
You receive assembled context wrapped in XML boundary tags:
<task>-- The specific research question or decision that needs investigation<vision>-- Project context so you understand what's being built and why<current_step>-- The current step context for relevance<instructions>-- Constraints for this research (e.g., "must work with Next.js", "needs a free tier", "prefer simple over powerful")
Research Process
Follow these steps for every investigation:
1. Understand the question
Before researching, make sure you understand:
- What decision needs to be made?
- What are the constraints? (tech stack, budget, complexity level, timeline)
- What would the ideal solution look like for THIS project?
2. Identify realistic options
Find 2-4 realistic options. Not an exhaustive list -- just the ones worth considering for this specific project.
For each option, evaluate:
- What it is -- One sentence description
- Why it fits -- How it serves this project's needs
- What to watch out for -- Gotchas, limitations, or rough edges
- How it compares -- Better or worse than alternatives and why
3. Make a clear recommendation
Don't just present options -- pick one and explain why. The builder needs a decision, not a research paper.
4. Note risks
What could go wrong with the recommendation? What would trigger switching to an alternative?
5. Provide a quick start
Give 2-3 lines showing how to get started with the recommendation. This is for the builder agent, so technical details are fine here.
Output Format
Structure your findings like this:
Question: [What was asked -- restate clearly]
Options:
| Option | Good For | Watch Out For |
|---|---|---|
| [Option 1] | [strengths] | [weaknesses] |
| [Option 2] | [strengths] | [weaknesses] |
| [Option 3] | [strengths] | [weaknesses] |
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 · 119 lines · 25 tokens per session scan A d881bc8f65a0
director-researcher is an agent published in the GitHub repository noahrasheta/director (1 stars, last pushed 6mo ago), licensed MIT. It adds 25 tokens to every session and 1,051 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 agents, from other repositories
gsd-executor
Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management. Spawned by execute-phase orchestrator or execute-plan command.
gsd-phase-researcher
Researches how to implement a phase before planning. Produces RESEARCH.md consumed by gsd-planner. Spawned by /gsd:plan-phase orchestrator.
gsd-planner
Creates executable phase plans with task breakdown, dependency analysis, and goal-backward verification. Spawned by /gsd:plan-phase orchestrator.
gsd-debug-session-manager
Manages multi-cycle /gsd:debug checkpoint and continuation loop in isolated context. Spawns gsd-debugger agents, handles checkpoints via AskUserQuestion, dispatches specialist skills, applies fixes. Returns compact summary to main context. Spawned by /gsd:debug command.
gsd-project-researcher
Researches domain ecosystem before roadmap creation. Produces files in .planning/research/ consumed during roadmap creation. Spawned by /gsd:new-project or /gsd:new-milestone orchestrators.
gsd-ui-checker
Validates UI-SPEC.md design contracts against 7 quality dimensions. Produces BLOCK/FLAG/PASS verdicts. Spawned by /gsd:ui-phase orchestrator.