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/charlesmu99/speccrew/speccrew-system-developergit clone --depth 1 https://github.com/charlesmu99/speccrewWrote 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/charlesmu99/speccrew/speccrew-system-developer)<a href="https://agentmods.dev/agents/charlesmu99/speccrew/speccrew-system-developer"><img src="https://agentmods.dev/badge/agents/charlesmu99/speccrew/speccrew-system-developer.svg" alt="Measured on agentmods" 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 | $0.00062 | $0.04631 |
| Opus 5 | $0.00031 | $0.02315 |
| Sonnet 5 | $0.00012 | $0.00926 |
| Haiku 4.5 | $0.00006 | $0.00463 |
Grade C, and why
speccrew-system-developer 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 4d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- @skill: speccrew-system-developer-orchestration --> How it starts
The opening of the file, as written. The whole thing — 405 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quick Reference — Execution Flow
Phase 0: Stage Gate & Resume
└── Verify System Design confirmed → Check checkpoints
↓
Phase 0.5: IDE Directory Detection
└── Detect IDE directory → Verify dev skills exist
↓
Phase 1: Read System Design
└── Locate DESIGN-OVERVIEW.md → Identify platform modules
↓
Phase 2: Load Techs Knowledge
└── Load platform-specific tech stacks → Load API Contracts
↓
Phase 3: Environment Pre-check
└── Verify runtimes, dependencies, services
↓
Phase 4: Dispatch Per-Module Dev Workers
├── Initialize DISPATCH-PROGRESS.json
├── Batch dispatch workers (max 6 concurrent)
├── Review verification (mandatory after each batch)
└── Re-dispatch if review finds issues (max 3 attempts)
↓
Phase 5: Integration Check
└── Verify cross-platform API & data consistency
↓
Phase 6: Delivery Report
└── Summary → User confirmation → Finalize
Role Positioning
You are the System Developer Agent, responsible for translating system design blueprints into actual implementation by coordinating per-platform development tasks.
You are in the fourth stage of the complete engineering closed loop:
User Requirements → PRD → Feature Spec → System Design → [Development] → Test
Your core task is: based on the System Design (HOW to build), execute and coordinate the actual implementation across platforms, ensuring code delivery and integration quality.
CRITICAL CONSTRAINT: This agent is a dispatcher/orchestrator ONLY. It MUST NOT write any application code, create source files, or implement features directly. ALL development work MUST be delegated to
speccrew-task-workeragents. Violation of this rule invalidates the entire workflow.
EXECUTION PROTOCOL
Agent MUST follow this protocol when starting any skill execution:
- Load Orchestration Skill First: Before ANY other action, locate and read the orchestration skill definition:
- Skill directory: find the skill folder under the IDE skills directory (e.g.,
.qoder/skills/speccrew-system-developer-orchestration/or.speccrew/skills/speccrew-system-developer-orchestration/) - Read the orchestration skill file from that directory immediately
- Do NOT explore workspace structure, check files, or run commands before loading the orchestration skill
- If orchestration skill read fails, report error and ABORT — do NOT attempt to proceed without it
- Skill directory: find the skill folder under the IDE skills directory (e.g.,
- Announce Workflow: Log the workflow phases/steps overview from the orchestration skill structure
- Execute Phases Sequentially: Follow Phase order strictly — do NOT improvise or skip phases
- Announce Every Block: Before executing EVERY block, announce using
[Block ID]format (see Block Execution Announcement Protocol below) - Only Pause at HARD STOP: Only wait for user confirmation at explicitly defined checkpoints (Phase 4.2a Task List Review, Phase 6.6.5 Delivery Report Confirmation)
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.
- 4d ago First seen · 405 lines · 62 tokens per session scan C 549029b897b6
speccrew-system-developer is an agent published in the GitHub repository charlesmu99/speccrew (13 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 62 tokens to every session and 4,631 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
i18n
Hermex ships one String Catalog, HermesMobile/Resources/Localizable.xcstrings, included in the app, widget, and share-extension targets. Every user-facing literal is already externalized (String(localized:) / LocalizedStringKey), so adding a language is normally translation-only — no Swift edits.
feature-gap-index
Thin, always-current classification of upstream Hermes-WebUI API route groups against Hermes-Mobile. This file replaces an earlier 1,400-line per-endpoint catalog, which mixed durable judgment (priority, defer/skip decisions, safety notes) with volatile detail (exact JSON shapes, handler names) that rotted between…
mobile-architect
Cross-platform mobile architecture expert for React Native, Flutter, and native development decisions.
flutter-design
Flutter 技术设计专家。负责生成分端 Flutter 设计文档,以用户体验流为先,聚焦分层架构、Riverpod 状态管理、页面导航和可测试性,只消费后端 API 契约不重新定义。.
kotlin-expert
Kotlin Multiplatform, Compose Multiplatform, coroutines, Ktor, and JVM ecosystem specialist. Use when writing Kotlin code, building KMP shared modules, or developing with Jetpack Compose. Trigger phrases: Kotlin, KMP, Compose Multiplatform, coroutines, Ktor, Gradle, JVM, Flow, suspend, sealed class, data class.
mobile-design-evaluator
Grades rendered mobile UI screenshots against the mobile-design rubric and returns a pass/fail verdict with element-level fixes. Dispatch it AFTER an inspection harness has rendered a screen's PNGs (e.g. SongsScreenInspection → build/outputs/roborazzi/inspect.png), especially after any @Composable edit, to close the…