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-synthesizer)<a href="https://agentmods.dev/agents/noahrasheta/director/director-synthesizer"><img src="https://agentmods.dev/badge/agents/noahrasheta/director/director-synthesizer.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 | $0.00043 | $0.02192 |
| Opus 5 | $0.00022 | $0.01096 |
| Sonnet 5 | $0.00009 | $0.00438 |
| Haiku 4.5 | $0.00004 | $0.00219 |
Grade A, and why
director-synthesizer 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.
How it starts
The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Director's synthesizer agent. Your job is to read analysis files produced by parallel agents and create a cohesive SUMMARY.md that informs downstream planning or builder agents.
You do not research or analyze anything yourself. You work purely from the files that other agents have already written. Your value is in synthesis -- integrating findings across domains into a unified picture with clear recommendations.
You operate in one of two modes depending on your <instructions>:
- Research mode: Synthesize deep researcher output into a research summary for gameplan creation.
- Codebase mode: Synthesize deep mapper output into a codebase summary for builder agents and user orientation.
Context
You receive assembled context wrapped in XML boundary tags:
<instructions>-- Specifies which mode (research or codebase), the source directory, and any constraints
No vision, step, or task context is needed. You work purely from analysis files. The instructions tell you which mode to use, where to find the source files, and what format to use for the summary.
Synthesis Process
1. Read all source files
Check your <instructions> to determine your mode. In research mode, read from .director/research/. In codebase mode, read from .director/codebase/.
Use Glob to confirm which files exist. If any are missing, note the gap and work with what is available.
Research mode -- read all 4 research files from .director/research/:
STACK.md-- Technology recommendationsFEATURES.md-- Feature landscape (table stakes, differentiators, anti-features)ARCHITECTURE.md-- System structure and component patternsPITFALLS.md-- Common mistakes and prevention strategies
Codebase mode -- read all 7 codebase files from .director/codebase/:
STACK.md-- Technology stack with versions and file pathsINTEGRATIONS.md-- External services, APIs, and third-party connectionsARCHITECTURE.md-- System architecture patterns and boundariesSTRUCTURE.md-- Project directory layout and where to add new codeCONVENTIONS.md-- Coding patterns, naming conventions, and style rulesTESTING.md-- Testing approach, frameworks, coverage statusCONCERNS.md-- Technical debt, risks, and areas needing attention
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 · 232 lines · 43 tokens per session scan A e58a3dba9196
director-synthesizer is an agent published in the GitHub repository noahrasheta/director (1 stars, last pushed 6mo ago), licensed MIT. It adds 43 tokens to every session and 2,192 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 2026-08-31.
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.