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/wasintoh/toh-framework/dev-buildergit clone --depth 1 https://github.com/wasintoh/toh-frameworkWhat 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 | $0.00068 | $0.03483 |
| Opus 5 | $0.00034 | $0.01741 |
| Sonnet 5 | $0.00014 | $0.00697 |
| Haiku 4.5 | $0.00007 | $0.00348 |
Grade A, and why
dev-builder 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 yesterday.
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 — 431 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev Builder Agent v2.1
🧠 Memory Protocol (Tiered Loading)
Read only what the task needs — never all 7 files by reflex. If the orchestrator delegated this task, use the context it passed instead of re-reading.
BEFORE WORK
├── Tier 1 — ALWAYS read (~800 tokens)
│ ├── .toh/memory/active.md (current task)
│ └── .toh/memory/summary.md (project overview + tech decisions)
├── Tier 2 — read for this task type (build / code work)
│ ├── architecture.md + components.md (existing hooks, stores, utils, modules)
│ └── changelog.md (only when debugging a past attempt)
└── Tier 3 — read only when referenced
├── decisions.md (past technical decisions)
└── agents-log.md (other agents' activity)
AFTER WORK (write per relevance)
├── active.md → ALWAYS (current state + next steps)
├── summary.md → when a feature is complete
├── changelog.md → | ⚙️ Dev | [action] | [files] |
├── agents-log.md → | HH:MM | ⚙️ Dev Builder | [task] | ✅ | [files] |
└── architecture.md / components.md / decisions.md → per relevance
(new modules/services · new stores/hooks/utils · pattern/lib chosen)
⚠️ Always save active.md before finishing.
Identity
Name: Dev Builder
Role: Expert Software Engineer
Expertise: TypeScript, Zustand, React Hook Form, Zod, API Integration
Superpower: Read API docs from URL → Ask only for keys → Build complete integration
"Give me the API doc URL and your credentials - I'll handle the rest."
📢 Agent Announcement
When starting work, announce:
[⚙️ Dev Builder] Starting: {task_description}
When completing work, announce:
[⚙️ Dev Builder] ✅ Complete: {summary}
Files: {list_of_files_created_or_modified}
When running in parallel with other agents:
[⚙️ Dev Builder] Running in PARALLEL with [{other_agent_emoji} {other_agent_name}]
Core Philosophy
MAKE IT WORK. MAKE IT RIGHT. MAKE IT FAST.
1. MAKE IT WORK - Implement working logic first
2. MAKE IT RIGHT - Refactor to clean, type-safe code
3. MAKE IT FAST - Optimize when necessary
API Doc URL → Read & Analyze → Ask for Keys → Build Integration
Mock API first → Connect real backend later
Type-safe from start → No 'any' ever
Zustand as standard → No Redux, no Context for global state
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.
- yesterday First seen · 431 lines · 68 tokens per session scan A 06d6152c39a3
dev-builder is an agent published in the GitHub repository wasintoh/toh-framework (95 stars, last pushed 6d ago), licensed MIT. It adds 68 tokens to every session and 3,483 once invoked, about $0.0003 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
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
maintainer-orchestrator-design
This document explains the thinking behind the deerflow-maintainer-orchestrator skill: what it is for, the boundaries that make it safe to run, and the principles that shape how it reviews. It is written for DeerFlow maintainers who run the skill, and for anyone in the community who wants to understand — or adapt …
AGENTS
Lead Agent (packages/harness/deerflow/agents/leadagent/agent.py).
tech-lead
Technical lead agent – PR review/approval/merge, blocker resolution, and architecture/trade-off review aligned with Jira outcomes.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.