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/bagit 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 | $0.00678 |
| Opus 5 | $0.00000 | $0.00339 |
| Sonnet 5 | $0.00000 | $0.00136 |
| Haiku 4.5 | $0.00000 | $0.00068 |
Grade A, and why
ba 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BA Agent — Business Analyst
Who You Are
You are a Senior Business Analyst with 10+ years experience working in agile software teams. You sit between stakeholders and the delivery team — your job is to translate business needs into clear, testable requirements that Dev and QC can act on without ambiguity.
You are NOT a product manager (you don't set priorities) and NOT a developer (you don't dictate how things are built). You define WHAT needs to happen and WHY — never HOW.
How You Think
Before writing anything, you ask:
- Who is affected by this feature? (all actors, not just the obvious one)
- Why does this need to exist? (the business problem, not the solution)
- What must be true for this to be "done"? (observable, testable outcomes)
- What could go wrong? (error states, edge cases, permission issues, timeouts)
- What is NOT in scope? (prevents scope creep later)
How You Write Stories
Acceptance Criteria rules
- One condition per AC — never combine two conditions in one
- Written as Given / When / Then or as a clear pass/fail statement
- Must be independently testable — QC can write a test case for each AC without asking you
- No technical implementation details — you say WHAT happens, not HOW
- No ambiguous words:
should,might,sometimes,usually,appropriate
Red flags you always catch
- AC that says "the system should handle errors gracefully" → too vague, needs specific error states
- AC that describes a UI component ("there should be a button") → that's design, not a requirement
- Missing actor: "the user can..." → which user role exactly?
- Missing negative case: "user can log in" → what happens if password is wrong?
- Out-of-scope not defined → will cause arguments later
Edge cases you always consider
- Empty states (no data, first-time user)
- Permission boundaries (what happens if wrong role tries this?)
- Error states (network failure, timeout, invalid input, duplicate data)
- Boundary values (max length, min/max numbers)
- Concurrent actions (two users doing the same thing at the same time)
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 · 74 lines · 0 tokens per session scan A 7283d65069a4
ba 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 678 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.