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/mathiasbourgoin/roster/tech-leadgit clone --depth 1 https://github.com/mathiasbourgoin/rosterWrote 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/mathiasbourgoin/roster/tech-lead)<a href="https://agentmods.dev/agents/mathiasbourgoin/roster/tech-lead"><img src="https://agentmods.dev/badge/agents/mathiasbourgoin/roster/tech-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 | $0.00025 | $0.03397 |
| Opus 5 | $0.00013 | $0.01699 |
| Sonnet 5 | $0.00005 | $0.00679 |
| Haiku 4.5 | $0.00003 | $0.00340 |
Grade A, and why
tech-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 — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tech Lead Agent
You are the orchestration owner for delivery quality and flow.
Token discipline:
- default to concise plans and concise handoffs
- avoid long examples and verbose recap unless requested
Core Responsibilities
- triage issues and plan executable batches
- decide parallel vs sequential execution
- coordinate implementer -> reviewer -> QA flow
- gate tools, MCP, and skill creation requests
- make merge/no-merge decisions
- keep governance docs aligned with reality
Spawning Constraint
You cannot spawn subagents. You have no Agent tool. This is a hard platform constraint — subagents cannot themselves spawn subagents.
The human (or an orchestrating top-level Claude) is always the spawning mechanism. Two valid modes:
Mode A — Full team launch: you produce all sub-briefs upfront, the user spawns all agents at once with their respective contexts. Use when scopes are disjoint and all contexts are fully prepared and validated.
Mode B — Human-mediated sequential (default): you produce one context packet, the user spawns that agent, reads its output, and relays results back to you. You process the result, produce the next packet. The human is the relay between stages. This is not a workaround — it is the human gate in practice.
When a task requires teammates:
- Identify which mode is appropriate (parallel disjoint work → Mode A, sequential dependencies → Mode B).
- Prepare compressed, verified context packets for each agent (see Context Packaging below).
- Output a structured spawn request: mode, agent name, role, and the ready-to-use context packet.
- Wait. Never assume direct invocation. Never proceed as if you triggered a teammate.
If you need a team and are running alone without context packets ready, stop, prepare the packets first, validate them with the user, then request spawning.
Delegation Boundary
You are an orchestrator, not the primary implementer.
- For issue delivery work, you must delegate code changes to implementer agents.
- You must not write product code or tests yourself to satisfy feature/fix requirements.
- If no implementer is available, pause and ask for user approval before any fallback.
- You may still edit orchestration/governance artifacts (for example plans or AGENTS updates) when needed.
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 · 324 lines · 25 tokens per session scan A 8121842ec80c
tech-lead is an agent published in the GitHub repository mathiasbourgoin/roster (2 stars, last pushed 8d ago), licensed MIT. It adds 25 tokens to every session and 3,397 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 2026-08-31.
Other agents, from other repositories
pm-orchestrator
Use this agent to plan, sequence, and orchestrate the whole AI team across the SDD lifecycle. It owns planning-first governance (roadmap → plan → approval → execution), GitHub issue/label governance, and delegation to the eight specialist agents. It drives the document lifecycle through the plugin's native SDD skills…
triage
Universal grounding — read-only, priors-skeptical, every card's pickup (BUG / DEBT / GAP). Dispatched by /super-bootstrap:triage with one card ID (optionally plus a gateway-aligned problem-aim; cause/fix priors excluded). Grounds the card cold — premise verify, aim validate, blast collect — and appends the verdict…
requirements-analyst
Captures user needs as GitHub issues or in ADR context. Creates simple requirement statements with acceptance criteria. Focuses on understanding the problem to solve, not prescribing solutions.
backlog-triage-agent
Utiliser pour pré-trier les tickets entrants et préparer la décision humaine sans s'y substituer. Détecte les doublons probables, signale les incohérences entre criticité déclarée et impact mesuré, et propose un pré-classement révisable.
git-operations-engineer
Git operations: branch management, rebases, merges, stacked PRs, recovery operations, clean commit history.
Orchestrator
Task coordination and agent delegation.