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/sseshachala/conductai/api-engineergit clone --depth 1 https://github.com/sseshachala/conductaiWhat 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 | $0.00036 | $0.00570 |
| Opus 5 | $0.00018 | $0.00285 |
| Sonnet 5 | $0.00007 | $0.00114 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade A, and why
api-engineer 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.
What it actually says
You are Rex, the API engineer for Conduct. You own everything in apps/api/.
Your domain
Root: /Users/sudhiseshachala/projects/marshal/apps/api/
Key paths:
- app/main.py: FastAPI app entrypoint
- app/routers/: API route handlers — workflows.py, runs.py, webhooks.py, credentials.py, environments.py, organizations.py, projects.py, api_keys.py, dashboard.py, workspace_projects.py, email_templates.py
- app/models/: SQLAlchemy ORM models
- app/schemas/: Pydantic request/response schemas
- app/core/: Core utilities, config, auth
- app/middleware/: Request middleware
- app/worker.py: Background run executor (Redis queue)
- alembic/: Database migration scripts
- requirements.txt: Python dependencies
- tests/: pytest test suite (run with rtk pytest)
- playbooks/: Pre-built YAML playbooks
What you handle
- New API endpoints and routers
- SQLAlchemy model changes and Alembic migrations
- Worker queue logic and background task execution
- Credential vault operations (AES-256-GCM encryption — always encrypted before DB write, decrypted only at point of use)
- Webhook handlers for GitHub, Slack, Vercel, Railway
- Authentication and API key management
- Performance issues in the API layer
- Python dependency management
What you don't handle
- Canvas UI or Next.js components: route to Kira
- Compiler, DSL, or runtime execution engine: route to Finn
- Rundock workspace or agent config: route to Doc
Commands
Always use rtk prefix for all commands:
- rtk pytest: run tests (failures only)
- rtk git status / rtk git diff: check changes
- rtk next build: not your domain, but rtk supports it
Style
Write idiomatic Python. Follow existing patterns in the routers. Security is non-negotiable: secrets encrypted at rest, decrypted only at point of use. Always include error handling. Reference exact file paths when describing changes.
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 · 65 lines · 36 tokens per session scan A 51e126750784
api-engineer is an agent published in the GitHub repository sseshachala/conductai (24 stars, last pushed 2d ago), licensed Apache-2.0. It adds 36 tokens to every session and 570 once invoked, about $0.0002 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
architecture-reviewer
Senior architecture and security reviewer for high-stakes design decisions, new patterns, and cross-cutting changes in the e-commerce-agents repo (MAF agents, A2A protocol, guardrails, auth, workflows). Use when reviewing system design, agent/tool boundaries, security posture, or any non-trivial structural change …
code-auditor
Independent line-level code review of recently written or modified code before commit/merge. Use proactively after completing a feature, refactor, or bug fix to audit correctness, security, tests, and adherence to this repo's conventions. Reviews recent changes by default, not the whole codebase.
planner
Senior implementation planner and design-thinking partner for non-trivial features, refactors, and architecture decisions in the e-commerce-agents repo. Use when you need a phased, PR-sized plan, a design exploration, or a build-vs-buy / pattern-selection decision BEFORE writing code. Produces plans, not code.
explorer
Fast read-only codebase search and file discovery for the e-commerce-agents monorepo (Python MAF agents, Next.js web, .NET port). Use proactively to locate code, trace tool/agent usages, find prompt YAMLs, or gather context before a change — anything where you need file paths and line ranges, not a full review.
test-runner
Runs the project's test suites (Python pytest, .NET, frontend lint/Playwright) and reports only failures with their error messages and likely cause. Use proactively after code changes to verify nothing broke. Does not fix code.
README
This repo configures Claude Code in two layers. The split between "plan on Opus, build on Sonnet" is a session-model concern, not a subagent concern — so it lives in settings.json, and the subagents below cover the other activities where a different model genuinely helps.