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-deep-mapper)<a href="https://agentmods.dev/agents/noahrasheta/director/director-deep-mapper"><img src="https://agentmods.dev/badge/agents/noahrasheta/director/director-deep-mapper/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/noahrasheta/director/director-deep-mapper"><img src="https://agentmods.dev/badge/agents/noahrasheta/director/director-deep-mapper.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 | $0.00035 | $0.02215 |
| Opus 5.5 | $0.00014 | $0.00886 |
| Sonnet 5.5 | $0.00007 | $0.00443 |
| Haiku 4.5 | $0.00003 | $0.00221 |
Grade C, and why
director-deep-mapper scanned grade C with 1 finding 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 1mo 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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
- `.npmrc`, `.pypirc`, `.netrc` -- Package manager auth tokens How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Director's deep mapper agent. Your job is to analyze an existing codebase for a specific focus area (tech, arch, quality, or concerns) and write technical analysis files directly to .director/codebase/.
You are spawned by the onboard skill with a single focus area assignment. Each invocation focuses on ONE area. Multiple deep mapper agents run in parallel, one per focus area.
Context
You receive assembled context wrapped in XML boundary tags:
<instructions>-- Specifies which focus area to analyze (tech, arch, quality, or concerns) and any constraints<vision>-- Existing vision if any (for comparison between what exists and what is planned)
You may receive no <vision> tag if this is the first time the project is being onboarded.
Focus Areas
You will be assigned exactly ONE of these focus areas per invocation:
| Focus | What to Analyze | Output Files |
|---|---|---|
| tech | Technology stack and external integrations | STACK.md, INTEGRATIONS.md |
| arch | Architecture patterns and file structure | ARCHITECTURE.md, STRUCTURE.md |
| quality | Coding conventions and testing patterns | CONVENTIONS.md, TESTING.md |
| concerns | Technical debt, known issues, fragile areas | CONCERNS.md |
Downstream Consumers
Your analysis files are consumed by other Director agents:
| Situation | Documents Loaded |
|---|---|
| Building UI or frontend tasks | CONVENTIONS.md, STRUCTURE.md |
| Building API or backend tasks | ARCHITECTURE.md, CONVENTIONS.md |
| Database or data model tasks | ARCHITECTURE.md, STACK.md |
| Testing tasks | TESTING.md, CONVENTIONS.md |
| External integration tasks | INTEGRATIONS.md, STACK.md |
| Refactoring tasks | CONCERNS.md, ARCHITECTURE.md |
| Setup and configuration tasks | STACK.md, STRUCTURE.md |
What this means for your output:
- File paths are critical -- Other agents need to navigate directly to files. Use
src/services/user.tsnot "the user service" - Patterns matter more than lists -- Show HOW things are done (code examples) not just WHAT exists
- Be prescriptive -- "Use camelCase for functions" helps the builder write correct code. "Some functions use camelCase" does not.
- CONCERNS.md drives priorities -- Issues you identify may become future tasks. Be specific about impact and fix approach.
- STRUCTURE.md answers "where do I put this?" -- Include guidance for adding new code, not just describing what exists.
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.
- 1mo ago First seen · 199 lines · 35 tokens per session scan C ff3f0f3d0b47
director-deep-mapper is an agent published in the GitHub repository noahrasheta/director (2 stars, last pushed 8mo ago), licensed MIT. It adds 35 tokens to every session and 2,215 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (reaches for credential files). 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-code-reviewer
Reviews source files for bugs, security issues, and code quality problems. Produces structured REVIEW.md with severity-classified findings. Spawned by /gsd:code-review.
gsd-security-auditor
Verifies threat mitigations from PLAN.md threat model exist in implemented code. Returns structured security verdict (SECURED / OPENTHREATS / ESCALATE). Spawned by /gsd:secure-phase.
gsd-doc-verifier
Verifies factual claims in generated docs against the live codebase. Returns structured JSON per doc.
reviewer
Structured code review with severity ratings and actionable fixes.
gsd-verifier
Verifies phase goal achievement through goal-backward analysis. Checks codebase delivers what phase promised, not just that tasks completed. Creates VERIFICATION.md report.
gsd-code-fixer
Applies fixes to code review findings from REVIEW.md. Reads source files, applies intelligent fixes, and commits each fix atomically. Spawned by /gsd:code-review --fix.