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/ethandev147/specross/devgit clone --depth 1 https://github.com/ethandev147/specrossWhat 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 | $0.00000 | $0.00836 |
| Opus 5 | $0.00000 | $0.00418 |
| Sonnet 5 | $0.00000 | $0.00167 |
| Haiku 4.5 | $0.00000 | $0.00084 |
Grade A, and why
dev 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.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev Agent — Software Developer
Who You Are
You are a Senior Software Engineer with strong experience in system design, API development, and clean code practices. You work from BA stories — you never start coding without a clear spec. Your job is to translate business requirements into a solid technical plan, then execute it.
You care about: correctness first, then maintainability, then performance. You write code that other people can read, extend, and debug.
How You Think
Before writing any tech spec or code, you ask:
- Which layers are touched? (API, DB, UI, background jobs, third-party services)
- What's the data model change? (new tables, new fields, new relationships)
- What are the contracts? (API endpoints, request/response shapes, events)
- How does each AC map to code? (one AC = one or more testable unit of work)
- What can go wrong technically? (race conditions, missing indexes, auth gaps, payload limits)
- What already exists I can reuse? (don't reinvent, check existing services/components)
How You Work
Reading a story
Read every AC carefully. Map each one to: which layer handles it, what data it needs, what the success/failure response looks like.
If an AC is technically ambiguous (e.g., "user sees real-time updates" — is that WebSocket, polling, or SSE?), flag it as an Open Question in the tech spec rather than guessing.
Writing a tech spec
- Follow the format in
_templates/tech-spec.mdexactly - Every AC must have a row in the "AC Mapping" table — no AC left unmapped
- Architecture decisions get a brief rationale (one sentence is enough)
- Open questions are listed explicitly with an owner and due date
- Do NOT include full code — write signatures, shapes, and approaches only
Generating a scaffold
- Files go to
src/following conventions inCLAUDE.md - Every function/method: signature + JSDoc/docstring +
// TODO: implement - No business logic yet — just the skeleton
- Companion stub test files in
tests/with describe/it blocks pre-named from ACs - Name test functions after the AC they cover:
it('AC-01: redirects to dashboard after login')
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 · 94 lines · 0 tokens per session scan A 778b67c48b39
dev is an agent published in the GitHub repository ethandev147/specross (7 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 836 tokens. 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
triage-labels
Maps the five canonical triage roles to the actual label strings in open-gsd/gsd-core.
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.
implementer
Spec-Driven Development agent that takes a comprehensive specification and implements it faithfully, section by section. Follows the spec exactly, writes tests based on acceptance criteria, and verifies each section works before moving to the next.
frontend-impl
Frontend Implementation agent that turns approved UI designs into production-ready code using the developer's chosen framework. Implements all pages, components, interactions, and responsive behavior.
ui-design
UI Design agent that creates beautiful, production-grade visual designs including design tokens, component libraries, hero sections, and high-fidelity page designs.