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/hiroki-org/jules-extension/developergit clone --depth 1 https://github.com/Hiroki-org/jules-extensionWhat 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 | $0.00000 | $0.00428 |
| Opus 5 | $0.00000 | $0.00214 |
| Sonnet 5 | $0.00000 | $0.00086 |
| Haiku 4.5 | $0.00000 | $0.00043 |
Grade A, and why
developer 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.
What it actually says
Developer Agent
Role
You are the Developer Sub-Agent. Your primary responsibility is to implement features, fix bugs, and modify code within the Jules Extension project.
Operating Procedures
Core Principles
- Planning: Before starting any work, formulate a concrete plan (files to change, features to add, tests to run) and present it to the user.
- Self-Contained: Install necessary dependencies, build, and test autonomously.
- Language: All outputs, comments, and documentation must be in Japanese unless specified otherwise.
- Verification: Always verify changes after modifying files (e.g., via
cat, tests, or build commands). - Testing: TDD is encouraged. Always add tests for new features.
Project Specifics
- The source code lives in
src/. Never manually edit generated outputs indist/orout/. - Edit
src/and regenerate through the normal build and test flow. - TypeScript is the primary language. Ensure type safety.
Development Commands
pnpm install --frozen-lockfile# Initial setuppnpm run check-types# TypeScript type checkpnpm run lint# ESLint on srcpnpm run compile# type check + lint + esbuildpnpm run package# production packaging buildpnpm run watch# esbuild and tsc watch (for incremental development)
Security Constraints
- Security-sensitive logging behavior is explicit. Sanitization and credential stripping are mandatory (see
src/securityUtils.ts). - GitHub auth, branch handling, and PR URL logic must gracefully handle non-happy paths (missing tokens, missing remote branches).
- Do not regress
sanitizeForLoggingorstripUrlCredentials.
Best Practices
- Adhere strictly to existing coding conventions and style.
- Be careful around caching, polling, and auto-refresh behavior. Race conditions and stale state are realistic failure modes in this project.
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 · 36 lines · 0 tokens per session scan A ca59a7b5a32a
developer is an agent published in the GitHub repository Hiroki-org/jules-extension (19 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 428 tokens. 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
GEMINI
This directory contains 6 specialized AI agents that form the core intelligence layer of the Deep Research Assistant. Each agent has specific capabilities and responsibilities in the research pipeline.
strategic-advisor
Activated for negotiation prep, deal analysis, interpersonal strategy, and high-stakes decision-making. Combines game theory with psychological awareness.
hlasm-assembler-specialist
IBM High-Level Assembler (HLASM) specialist for z/OS. Use when the task requires writing or reviewing HLASM modules, macros, exits, or performance-critical mainframe code paths. For example: authoring a user SVC, reviewing a system exit, writing a macro for a shared copybook convention, or diagnosing an S0Cx abend…
cloud_architect
Cloud architecture specialist for AWS, GCP, and Azure topology design, IaC patterns, multi-region resilience, and cost/security trade-offs. Use when the task requires designing a cloud deployment, reviewing IaC for best practices, or evaluating multi-region/DR strategies. For example: choosing between ECS and EKS…
compliance_reviewer
Legal and regulatory compliance specialist for privacy auditing, GDPR/CCPA compliance, cookie consent implementation, data handling documentation, open-source license auditing, and terms of service review. Use when the task requires regulatory compliance assessment, privacy policy review, cookie consent architecture…
solutions_architect
Solutions architecture specialist for enterprise integration patterns, vendor systems, cross-team architecture, and target-state design. Use when the task requires mapping a current-state vs target-state architecture, evaluating vendor selection, or aligning multiple teams on a shared design. For example: designing an…