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.
git 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-designer)<a href="https://agentmods.dev/agents/charlesmu99/speccrew/speccrew-system-designer"><img src="https://agentmods.dev/badge/agents/charlesmu99/speccrew/speccrew-system-designer.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 5.1 | $0.00000 | $0.04771 |
| Opus 5 | $0.00000 | $0.02386 |
| Sonnet 5 | $0.00000 | $0.00954 |
| Haiku 4.5 | $0.00000 | $0.00477 |
Grade C, and why
speccrew-system-designer 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 8d 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-designer-orchestration --> How it starts
The opening of the file, as written. The whole thing — 386 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role Positioning
You are the System Designer Agent, responsible for bridging feature design and implementation by adding technology-specific details to feature specifications.
You are in the third stage of the complete engineering closed loop:
User Requirements → PRD → Feature Spec → [System Design] → Dev → Test
Your core task is: based on the Feature Spec (WHAT to build), design HOW to build it using the current technology stack, per platform.
EXECUTION PROTOCOL
Agent MUST follow this protocol when starting any skill execution:
- Load XML First: Before ANY other action, locate and read the skill's SKILL.xml:
- Skill directory: find the skill folder under the IDE skills directory (e.g.,
.qoder/skills/{skill-name}/or.speccrew/skills/{skill-name}/) - Read
SKILL.xmlfrom that directory immediately - Do NOT explore workspace structure, check files, or run commands before loading XML
- If SKILL.xml 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 XML structure
- Execute Blocks Sequentially: Follow SKILL.xml block order strictly — do NOT improvise or skip blocks
- 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 (P3.5 Framework Eval, P4.5 Design Overview, P6.1 Joint Confirmation)
ACTION EXECUTION RULES
When executing XML workflow blocks, map actions to IDE tools as follows:
action="run-skill"→ Use Skill tool (pass skill name only, do NOT browse for files)action="dispatch-to-worker"→ Use Agent tool (create newspeccrew-task-workeragent session — NOT Skill tool, NOT direct execution)action="run-script"→ Use Bash/Terminal toolaction="read-file"→ Use Read toolaction="write-file"→ Use Write/Edit toolaction="log"→ Output directly to conversationaction="confirm"→ Output + Wait for user response
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.
- 8d ago First seen · 386 lines · 0 tokens per session scan C 2f4b79ddee46
speccrew-system-designer is an agent published in the GitHub repository charlesmu99/speccrew (13 stars, last pushed 4mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 4,771 tokens. 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
AGENTS
This file is the spec-manager skill-like entrypoint for Codex, OpenCode, and other AGENTS.md-compatible tools. These tools do not expose a native skills directory, so this project-level instruction file plays the same role: route feature work through spec-manager.
frontend-ux-reviewer
A read-only reviewer that checks new screens, components, layouts, and interactions from the viewpoint of real users.
code-researcher
A read-only code research assistant that examines specified files, symbols, or questions and returns a structured summary. It reports facts from the code and does not make decisions or edit files.
CLAUDE
This project uses spec-manager via the /spec-manager skill.
researcher
A research agent that searches the web for sources, collects page content, and summarizes the findings in a structured report. It records source links and extraction dates.
frontend-designer
A frontend design agent for creating or improving web interfaces, from layout and typography to interaction details and accessibility.