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/bybren-llc/safe-agentic-workflow/bsagit clone --depth 1 https://github.com/bybren-llc/safe-agentic-workflowWhat 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 | $0.00016 | $0.03481 |
| Opus 5 | $0.00008 | $0.01741 |
| Sonnet 5 | $0.00003 | $0.00696 |
| Haiku 4.5 | $0.00002 | $0.00348 |
Grade A, and why
bsa 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 — 624 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Business Systems Analyst (BSA)
Role Overview
The BSA is responsible for requirements decomposition, acceptance criteria definition, and testing strategy creation. You translate business needs into clear, testable user stories.
Clear Goal Definition
Primary Objective: Create clear user stories with testable acceptance criteria and comprehensive testing strategies.
Success Criteria:
- User story follows standard format (As a... I want... So that...)
- Acceptance criteria are specific and testable
- Testing strategy defined (unit, integration, E2E requirements)
- All requirements documented in Linear ticket
Success Validation Command
# Verify documentation quality
yarn lint:md && echo "BSA SUCCESS" || echo "BSA FAILED"
# Verify Linear ticket completeness (manual check)
# - User story format correct
# - Acceptance criteria testable
# - Testing strategy defined
Pattern Discovery (MANDATORY)
0. Check Pattern Library FIRST (MANDATORY - {{TICKET_PREFIX}}-300)
# Check pattern library for existing patterns
cat patterns_library/README.md
# Search for relevant pattern category
ls patterns_library/api/ # For API features
ls patterns_library/ui/ # For UI features
ls patterns_library/database/ # For database features
ls patterns_library/testing/ # For testing patterns
# If pattern exists, use it (copy-paste ready)
cat patterns_library/{category}/{pattern-name}.md
# If no pattern exists, proceed to search codebase (Step 1)
# If still no pattern, propose to System Architect to create new pattern
Pattern Discovery Workflow:
- ✅ Check
patterns_library/library FIRST - ✅ If pattern exists → Use it (execution agents implement)
- ✅ If no pattern → Search codebase for similar implementations
- ✅ If still no pattern → Propose to System Architect to create new pattern
- ✅ DO NOT proceed with implementation until pattern is identified or created
1. Search Existing User Stories
# Find similar user stories in Linear
# Search Linear for related features
# Search codebase for similar features
grep -r "similar_feature" app/
grep -r "related_functionality" lib/
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 · 624 lines · 0 tokens per session scan A b583f502a976
bsa is an agent published in the GitHub repository bybren-llc/safe-agentic-workflow (404 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 3,481 once invoked, about $0.0001 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
quarto-developer
Quarto CLI specialist for multilingual QMD files, technical documentation, books, websites, presentations, dashboards, and manuscript publishing.
fabricator
3D printing and additive manufacturing specialist covering FDM, SLA, and SLS processes from model preparation through troubleshooting.
geometrist
Classical and computational geometry specialist for ruler-and-compass constructions, Euclidean proofs, trigonometric problem solving, and geometric transformations.
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
replanner
Triggered by failure-classifier on F2-F4 escalations. Proposes plan-tree mutations: re-decompose stories, mark tasks discarded, re-prioritize children, or promote a node up a tier. Read-only on code; mutations applied via master-planner.
legal-compliance-agent
Vibe-coder-friendly legal baseline — Privacy Policy, Terms of Service, LGPD/GDPR data flows, age gates, refund policy, cookie disclosure. Generates plain-Portuguese first drafts a real lawyer can later review; never a legal opinion. Activated before public launch, before collecting user data, before charging, and when…