tech-lead

tech-lead is an agent for Claude Code from atretyak1985/swarmery. It costs 40 tokens per session (1,473 once invoked), scanned A, original, Apache-2.0.

A technical-lead coordinator that directs executor agents through a nine-phase workflow. It classifies the task, looks for missing information, considers risks before work starts, selects a working mode, and records phase changes.

In plain words
What is it for?
Use it to triage tasks, coordinate executor agents, run gap analysis and a pre-mortem, route work between modes, and log workflow phases.
Why use it?
It gives multi-agent coding work a defined process for deciding how to proceed, finding gaps, and tracking transitions.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; mentions subagents.

Part of the core plugin — 36 skills, 8 commands, 13 agents shipped together

Good fit Use it to triage tasks, coordinate executor agents, run gap analysis and a pre-mortem, route work between modes, and log workflow phases.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/atretyak1985/swarmery/tech-lead
Install

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.

Clone the repo
git clone --depth 1 https://github.com/atretyak1985/swarmery

Made for: Claude Code.

Or install core, the plugin that ships this one along with the rest of its 36 skills, 8 commands, 13 agents.

Wrote 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.

agentmods badge for tech-lead

README.md
[![agentmods](https://agentmods.dev/badge/agents/atretyak1985/swarmery/tech-lead.svg)](https://agentmods.dev/agents/atretyak1985/swarmery/tech-lead)
Your own site
<a href="https://agentmods.dev/agents/atretyak1985/swarmery/tech-lead"><img src="https://agentmods.dev/badge/agents/atretyak1985/swarmery/tech-lead.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,473 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00040 $0.01473
Opus 5 $0.00020 $0.00737
Sonnet 5 $0.00008 $0.00295
Haiku 4.5 $0.00004 $0.00147

Measured 4d ago against content hash f23b45e0c130, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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.

plugins/core/agents/tech-lead.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

You are the orchestrator for structured development work. You do not write production code yourself — you understand the task, decide how much process it deserves, delegate to executors, judge their output, and close the loop. Use your own judgment over ceremony: the phases below are a routing guide, not a ritual.

Operate

  1. Understand first. Read enough of the code to know what the task really is. Split what you don't know into things the codebase can answer (go look, or send @researcher) and things only the user can answer — ask those immediately and do not start implementation until they're resolved.
  2. Route by size and nature.
    • Bug: dispatch @debugger for root cause before anyone plans a fix.
    • Small (single file, well understood): hand @implementation-agent one focused brief, or fix it yourself if delegation costs more than the work.
    • Medium: have @planner produce a short plan, then run 2–3 executors (implementation, tests) against it, in parallel when independent.
    • Large / codebase-wide (multi-repo, schema changes, "from every angle"): bring in @architect for design first, and prefer the platform's native dynamic workflow orchestration over hand-rolling your own fan-out.
  3. Always gate before commit. An independent read-only @code-reviewer pass (plus @security-auditor when the change touches auth, input handling, secrets, or infra) reviews the diff. Route verdicts honestly: fix findings or record why not; two failed re-dispatches on the same point → stop and escalate to the user.
  4. Track progress where the platform reads it. Work in a workspace task dir (${AGENT_WORKSPACE_ROOT}/${AGENT_PROJECT}/workspace/working/{YYYY}/{MM}/{DD}/{slug}/, task-id yyyy-mm-dd-slug). Tick each satisfied acceptance checkbox - [ ]- [x] in the phase doc immediately after verifying it — the dashboard derives all progress from those checkboxes; never tick unsatisfied ones. Keep checkpoint.json current enough that a cold resume knows the next action.

Read the full file on GitHub · 132 lines

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.

  1. 4d ago Changed · -376 lines · +2 tokens per session f23b45e0c130
  2. 7d ago First seen · 508 lines · 38 tokens per session scan A 7e4b6f80be4e

Subscribe to this mod's changes

tech-lead is an agent published in the GitHub repository atretyak1985/swarmery (4 stars, last pushed today), licensed Apache-2.0. It adds 40 tokens to every session and 1,473 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 2026-08-31.

Related

Other agents, from other repositories

docs-scribe

Use this agent to maintain the inward-facing documentation that lives inside fakoli-state: the docs/ folder (specs, runbooks, design notes, plan archives), the plugin's CHANGELOG.md, and the description field of .claude-plugin/plugin.json. Audits cross-references between docs — broken [[wikilinks]], mismatched section…

fakoli/fakoli-plugins · 723 tokens

marketplace-scribe

Use this agent to maintain the marketplace-level artifacts that surface fakoli-state to first-time visitors: .claude-plugin/marketplace.json, the root README.md plugins table, and the registry/.json index files. Fires after any version bump, agent add/remove, or skill add/remove inside fakoli-state — these are the…

fakoli/fakoli-plugins · 657 tokens

warden

Use this agent when you need a security review — injection surfaces, secret and credential leakage, dependency and supply-chain risk, and plugin permission surfaces (hooks, tool allowlists, MCP configs). Wardens report; they don't fix. Context: A new feature added an endpoint that shells out based on user input. user…

fakoli/fakoli-plugins · 389 tokens

planner

Use this agent when you need to turn a parsed fakoli-state PRD into a coherent task graph — propose Features that group related Requirements, draft Tasks with acceptance criteria and verification commands, and surface high-complexity tasks that should be expanded. Specializes in the PRD-to-tasks transformation; defers…

fakoli/fakoli-plugins · 396 tokens

audit-ecosystem

Audits MCP servers, plugins, and hooks against expert knowledge. Dispatched by /claudit during Phase 2.

acostanzo/quickstop · 29 tokens

audit-global

Audits global Claude Code configuration (/.claude/) against expert knowledge. Dispatched by /claudit during Phase 2.

acostanzo/quickstop · 29 tokens