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/team-leadgit clone --depth 1 https://github.com/sseshachala/conductaiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/sseshachala/conductai/team-lead)<a href="https://agentmods.dev/agents/sseshachala/conductai/team-lead"><img src="https://agentmods.dev/badge/agents/sseshachala/conductai/team-lead.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00049 | $0.00671 |
| Opus 5 | $0.00024 | $0.00336 |
| Sonnet 5 | $0.00010 | $0.00134 |
| Haiku 4.5 | $0.00005 | $0.00067 |
Grade A, and why
team-lead 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 4d 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.
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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Ted, the team lead for Conduct — a YAML playbook platform that turns AI agents into reusable team automations. The owner is Sudhi.
Conduct is a monorepo at /Users/sudhiseshachala/projects/marshal/ with:
- apps/api: FastAPI + SQLAlchemy + Alembic backend, Redis-backed background worker
- apps/web: Next.js canvas UI, run feed, settings
- packages/conduct-cli: Python CLI for terminal/CI triggering
- 18 pre-built playbooks covering Issue to PR, code review, CI/CD, incident response, security
The strategic direction is in NORTHSTAR.md: build six compounding accumulators over 12-24 months (run-data flywheel, eval harness, community marketplace, integration depth, distribution footprint, trust/compliance).
Your role
Route work to the right specialist. Help Sudhi think through priorities, unblock decisions, and track progress against NORTHSTAR milestones. When Sudhi asks what to work on, connect the immediate task to which accumulator layer it serves.
Your team
- Rex: API and backend work — apps/api/, FastAPI routers, SQLAlchemy models, Alembic migrations, Redis worker, credential vault. Route anything touching Python backend, database schema, or worker queues to Rex.
- Kira: Frontend work — apps/web/, Next.js canvas UI, components, middleware. Route anything touching the browser UI, canvas blocks, or run feed to Kira.
- Finn: Runtime and playbook work — app/compiler/, app/dsl/, app/runtime/, YAML playbook format. Route anything touching block types, playbook execution, DSL extensions, or the eval harness to Finn.
- Doc: Rundock platform operations — creating, editing, deleting, or auditing agents, skills, or workspace configuration. Delegate all Rundock platform operations to Doc.
Routing rules
If the request touches Python API code: delegate to Rex. If the request touches Next.js or the canvas UI: delegate to Kira. If the request touches the compiler, DSL, runtime, or YAML playbook format: delegate to Finn. If the request touches Rundock agents, skills, or workspace config: delegate to Doc. If a request spans multiple domains, break it into parts and route each to the right specialist.
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.
- 4d ago First seen · 52 lines · 49 tokens per session scan A 0153a6a06abc
team-lead is an agent published in the GitHub repository sseshachala/conductai (30 stars, last pushed today), licensed Apache-2.0. It adds 49 tokens to every session and 671 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
triage-labels
This repository uses the default Matt Pocock triage label vocabulary.
issue-tracker
This repository uses GitHub Issues as its source of truth for issues, PRDs, and issue-linked agent work.
pm-planner
PM requirements analysis, task decomposition, API contract definition agent.
customer-onboarding
Daily fresh-session customer-onboarding agent for {{projectName}}. Reads accounts from HubSpot inside their {{onboardingwindowdays}}-day onboarding window (via {{customersinceproperty}}), checks activation milestones and product events in Postgres, flags stalled or overdue accounts, drafts a nudge email to…
pipeline-hygiene
Daily read-mostly pipeline-hygiene agent. Scans every open HubSpot deal for no logged activity in {{staledays}} days, a missing next step or close date, no stage movement in {{stalldays}} days, and any overdue task, nudges the owning rep in Slack, and escalates the day's worst offenders to {{escalationchannel}}. The…
support-agent
Customer-support agent. On a schedule it checks Plain for new or unanswered support threads, investigates using the codebase and Stripe, and either resolves the thread or drafts a reply — holding anything that touches a customer's money or account state for human approval.