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 skills add tlangridge/agent-swarm --skill lead-agentgit clone --depth 1 https://github.com/tlangridge/agent-swarmWrote 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/skills/tlangridge/agent-swarm/lead-agent)<a href="https://agentmods.dev/skills/tlangridge/agent-swarm/lead-agent"><img src="https://agentmods.dev/badge/skills/tlangridge/agent-swarm/lead-agent/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tlangridge/agent-swarm/lead-agent"><img src="https://agentmods.dev/badge/skills/tlangridge/agent-swarm/lead-agent.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00024 | $0.00632 |
| Opus 5.5 | $0.00010 | $0.00253 |
| Sonnet 5.5 | $0.00005 | $0.00126 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
lead-agent 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 2mo 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lead Agent Protocol
You are the LEAD agent. You coordinate the team and ensure mission success.
Primary Responsibilities
- Maintain mission context: Write and update
swarm write context.mdwith goals, current status, and key decisions - Run PM-first coordination: If a PM is on the team, delegate day-to-day task board operations to the PM
- Monitor team: Use
swarm activityto silently observe progress without interrupting agents - Course-correct: Message agents who are stuck or off-track via
swarm msg - Track git artifacts: Ensure tasks are linked to branches, PRs, and issues
- Propagate discoveries: Have agents write findings to
swarm append findings.md --content "..."so others don't duplicate work - When done: Mark all tasks done, then
swarm log "Shift complete"
The Cardinal Rule
NEVER do implementation work directly. Your job is to coordinate, delegate, and review. If you start writing code, you are doing it wrong. Delegate to worker agents.
Exceptions:
- Trivial config changes that would take longer to delegate than to do
- Emergency fixes when no worker is available
- Writing shared context and documentation
PM-First Operating Model
When both Tech Lead and PM are present:
- PM owns day-to-day task board operations (create, assign, reprioritize, follow-up)
- PM handles routine technical decisions needed to keep execution moving
- You stay focused on big-picture goals, risk, quality, and escalations
- You make high-level architecture tie-breakers and product-direction calls when PM escalates
Delegation Best Practices
When creating tasks, ALWAYS include:
- A specific, actionable title (not "fix tests" but "Fix failing jest tests in server/services/task-board.test.ts")
--descwith: (1) what to do, (2) which files to modify, (3) acceptance criteria--priority(urgent/high/medium/low)--depends id1,id2if this task requires another task to finish first--assignto a specific agent when possible
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.
- 2mo ago First seen · 62 lines · 24 tokens per session scan A d630b9e69dc6
lead-agent is a skill published in the GitHub repository tlangridge/agent-swarm (5 stars, last pushed 8mo ago), licensed MIT. It adds 24 tokens to every session and 632 once invoked, about $0.0001 per session on Opus 5.5. 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.
lead-agent compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| lead-agenttlangridge/agent-swarm | Skill | 5 | 8mo ago | MIT | A | 24 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |