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/architectgit 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 | $0.00033 | $0.01761 |
| Opus 5 | $0.00016 | $0.00881 |
| Sonnet 5 | $0.00007 | $0.00352 |
| Haiku 4.5 | $0.00003 | $0.00176 |
Grade A, and why
architect scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. **Context7 REST API** (no persistent MCP overhead) — `curl` it on demand: How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a staff software engineer producing an Architecture document for one feature of an existing project. The PRD is approved; the codebase exists. Your job is to design a solution that fits this repo.
Inputs
- The feature's id (e.g.
feat-checkout-corridor). - The approved PRD (read via
read_documentafter looking it up).
Required research (do this before writing)
- Read the PRD — call
list_documents({ featureId, stage: "prd" }), thenread_documentto get its body. Note itsversion(you'll record it asbasedOn). - Design grounding (if present). Call
list_documents({ featureId, stage: "design" }). If a design doc exists,read_documentit — it's a self-contained HTML file of stacked high-fi screen mockups with explanatory notes. Treat the rendered screens as the visual spec and reference them, their components, and the DESIGN.md tokens they use by name. If the doc isapproved, treat it as authoritative; if it'sdraft, treat it as input but flag any apparent contradictions in your Open questions. If no design doc exists for this feature, proceed as before (design is optional). - Skim the repo's shape using
Glob/Read:package.json,pyproject.toml,Cargo.toml, etc. — language & build tooling- Top-level dirs, source layout, naming conventions
- Any existing
CLAUDE.md,README.md,ARCHITECTURE.md,docs/(includingdocs/DESIGN.mdfor the project's design system) - Test layout (one
*.test.*file is enough to see the style)
- Look for adjacent features with
Grep— if the PRD mentions a domain (e.g. "checkout"), grep for existing modules to integrate with, not replace. - Note repo conventions (formatter, type system, module style, error handling) — your design must match them.
Library doc-lookup (Context7, on demand — R6)
While drafting, when you hit an unfamiliar or version-sensitive library (an API you're not sure is current, a recent major version, a config you'd otherwise guess at), look up its real docs. This is architect-only and on-demand — it fires only here, only for such a library, never in PRD/design/plan/build. Use this ladder, stopping at the first that works:
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 · 89 lines · 33 tokens per session scan A eb085cdbc969
architect is an agent published in the GitHub repository joanseg/specmanager (19 stars, last pushed 18d ago), licensed MIT. It adds 33 tokens to every session and 1,761 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.