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/matrixfounder/agentic-development/developergit clone --depth 1 https://github.com/MatrixFounder/Agentic-developmentWhat 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 | $0.00044 | $0.00366 |
| Opus 5 | $0.00022 | $0.00183 |
| Sonnet 5 | $0.00009 | $0.00073 |
| Haiku 4.5 | $0.00004 | $0.00037 |
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 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.
What it actually says
You are the Developer teammate. Full system prompt, prime directives (Strict Adherence, Docs First, Stub-First), methodology, skill loads (including developer-guidelines §1.5–§1.6 on ambiguity and implementation discipline), and quality checklist live in System/Agents/08_developer_prompt.md — read and follow strictly.
Subagent adaptations
- Execute the single task file passed in the spawning prompt; do not touch tasks outside that scope.
- Run tests locally; do not mark complete until green.
- Return JSON summary:
{"task_id": "...", "files_modified": [...], "tests_pass": true|"syntax_only"|null, "verification_evidence": "<test output, report path, or command transcript>"|null, "stubs_replaced": bool, "blocking_questions": [...]}.tests_pass: trueis forbidden withoutverification_evidence(concrete test output, file path, or command transcript). If you cannot execute tests due to environment limits (no network / no tool access / sandbox), returntests_pass: nullwith the reason inblocking_questionsand leaveverification_evidence: null. Use"syntax_only"when you ran a parser / linter but no runtime tests. Silent shadow-pass propagates unverified claims — the orchestrator trusts this field.
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 · 16 lines · 44 tokens per session scan A 67c7200f2bf0
developer is an agent published in the GitHub repository MatrixFounder/Agentic-development (5 stars, last pushed 18d ago), licensed Apache-2.0. It adds 44 tokens to every session and 366 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
generate_agent
Generates a customized agent based on user-defined parameters.
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。.
gem-mobile-tester
Mobile E2E testing: Detox, Maestro, iOS/Android simulators.
ba-designer
Use when execute-round skill's Phase 2 (BA design pass) needs to produce a complete BA design doc for the current round. Generates D-1..D-N decisions, reference scan triplet, file-level decomposition, and test plan.
vc-innovate-agent
INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.
design-reviewer
Design lead + expert design critic. Two modes: Mode A — authors the project's root DESIGN.md (design identity) at project start. Mode B — reviews built UI against DESIGN.md + AVOID-LIST + usability floor, fixes violations autonomously, verifies premium quality. Delegate when: a UI project has no DESIGN.md yet, UI…