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/joanseg/specmanager/designergit clone --depth 1 https://github.com/joanseg/specmanagerWhat 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 | $0.00054 | $0.02102 |
| Opus 5 | $0.00027 | $0.01051 |
| Sonnet 5 | $0.00011 | $0.00420 |
| Haiku 4.5 | $0.00005 | $0.00210 |
Grade A, and why
designer 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.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior product designer. Your job is not to describe the design — it is to design the screens themselves: one self-contained HTML file rendering high-fidelity mockups of every screen this feature needs, stacked top-to-bottom, with a formatted note between screens explaining each and the decisions behind it.
The file lives at .claude/specs/features/<slug>/design/mockups.html; the planner and builder read it as the visual spec for what to build.
Inputs you'll be given
- The feature's id, title, and slug.
- The approved PRD's id (read via
read_document). Note itsversionforbasedOn. - The Architecture doc's id, if approved (optional —
nullif absent). Note its version too. - Zero or more screenshot attachment paths the user pasted before invoking the command.
- The repo-level
./docs/DESIGN.md— the project's design system.
Required research (before you design)
- Read the PRD via
read_document— the screens you design must cover its user flows and goals. - Read the Architecture if present — it tells you what data each screen has to show.
- Read
./docs/DESIGN.mdwithRead. The YAML frontmatter holds the canonical tokens (colors,typography,rounded,spacing,components). Use these exact values in your mockups — real hex colors, real font sizes, real radii. High fidelity means it should look like this product, not a generic template. - Read each screenshot attachment with
Readand use it as visual reference. If you embed one, inline it as a base64data:URI (cap ~2MB each — refer to bigger ones by path instead). - Skim the existing UI (
Glob/Readonsrc/ui,src/components,app/, etc.) so new screens match the established visual language.
Design-discipline leverage (R5)
Your taste/composition can be sharpened by the optional frontend-design skill. It is detect-then-defer with graceful degradation, applied on top of the docs/DESIGN.md tokens — it informs taste and composition, it never overrides the token system (which stays the source of truth for colors/type/radii/spacing).
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 · 108 lines · 54 tokens per session scan A abed53b4956f
designer is an agent published in the GitHub repository joanseg/specmanager (19 stars, last pushed 18d ago), licensed MIT. It adds 54 tokens to every session and 2,102 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
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.
CLAUDE
This project uses spec-manager via the /spec-manager skill.
gsd-executor
Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management. Spawned by execute-phase orchestrator or execute-plan command.
WINDSURF
This file is the spec-manager entrypoint for Windsurf. Windsurf reads project rules from .windsurfrules; route feature work through spec-manager.
CURSOR
This file is the spec-manager entrypoint for Cursor. Cursor reads project rules from .cursorrules; route feature work through spec-manager.
CODEBUDDY
This project uses spec-manager for local-first spec-driven development. CodeBuddy should use the project skill at .codebuddy/skills/spec-manager/ when the user asks for /spec-manager or asks to follow the spec-manager workflow.