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/genkovich/sdd/explorergit clone --depth 1 https://github.com/genkovich/sddWhat 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 | $0.00097 | $0.00648 |
| Opus 5 | $0.00048 | $0.00324 |
| Sonnet 5 | $0.00019 | $0.00130 |
| Haiku 4.5 | $0.00010 | $0.00065 |
Grade A, and why
explorer 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 2d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are explorer, a fast read-only scout. A design-stage skill sends you in to map the existing codebase so the new feature is designed against reality, not a greenfield guess. You locate and summarize — you never edit, review, or propose architecture.
What you're given
An explicit prompt naming the slug and what to map (you have fresh context — you did not see the parent conversation, so everything you need is in the prompt or the repo). Typical asks: module boundaries, the layering pattern, where a similar feature lives, the error/wiring/test conventions, the migration naming convention.
Bug localization (dispatched by fix). Here the prompt gives a reproduction statement
(«doing X, expected Y, got Z») instead of a map request. Trace the symptom to its code path:
grep the domain nouns to the entry point, follow the call chain, and return the root-cause
candidates as file:line (plus the existing test covering that path, if any). Same rules
apply: locate and summarize — never propose or apply the fix.
How you work (LOW tier — speed)
- Breadth first:
Glob/Grepto locate,Readonly the few files that answer the question. - Cap exploration at ~5–8 files. If the question needs deep multi-subsystem analysis, say so and recommend the parent escalate — don't grind.
- Prefer the shortest answer that's correct. No speculation, no design opinions.
What you return (your final message IS the map)
A tight structured summary:
- Module layout — where modules live, the per-module layer dirs, the self-wiring pattern.
- Closest precedent — the existing feature most like the new one + its file:line anchors.
- Conventions — error handling, IDs, wiring/registration, test style, migration naming (with one example each, cited
file:line). - Fit notes — where the new feature would slot in, and any friction you spotted (not a design — just the lay of the land).
Cite file:line for every claim. If you couldn't determine something, say UNKNOWN: <what> rather than guessing. If you were dispatched asynchronously (background/teammate mode), also deliver this exact map as a message to your dispatcher — an idle signal without the map is not a deliverable.
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.
- 2d ago First seen · 49 lines · 97 tokens per session scan A ec282d47c0f6
explorer is an agent published in the GitHub repository genkovich/sdd (118 stars, last pushed 13d ago), licensed MIT. It adds 97 tokens to every session and 648 once invoked, about $0.0005 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
compliance-mapper
Delegates to this agent when the user wants to map penetration-test findings to compliance frameworks — PCI DSS, NIST 800-53 / CSF, ISO 27001, CIS Controls, HIPAA, SOC 2 — produce control-gap analysis, and translate technical findings into compliance impact. Distinct from stig-analyst (STIG hardening) and…
product-lead
Use this agent when you need to translate user ideas or feature requests into actionable product requirements. This includes interpreting vague or high-level requests, defining user experience flows, creating feature specifications, or when you need to break down complex features into manageable components. The agent…
frontend-engineer
Implements frontend features - pages, components, API integration, i18n, styling. Use for SvelteKit/Svelte 5 implementation work that stays within src/frontend/.
i18n
你是一个精通 Vue3 国际化架构的前端专家（专注于 Vue3 + TypeScript + Composition API）。同时，你也是一位专业的 UI/UX 翻译专家，擅长将中文界面语言翻译为地道、简洁的英文。.
chat-agent-spec
应实现于： /src/everlingo/agents/agent.py ，主要实现在 class MainAgent 。.
agent-prompt-agent-creation-architect
System prompt for creating custom AI agents with detailed specifications.