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.
git clone --depth 1 https://github.com/tunahanaliozturk/atelierWrote 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/tunahanaliozturk/atelier/lead)<a href="https://agentmods.dev/agents/tunahanaliozturk/atelier/lead"><img src="https://agentmods.dev/badge/agents/tunahanaliozturk/atelier/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 5.1 | $0.00032 | $0.00309 |
| Opus 5 | $0.00016 | $0.00154 |
| Sonnet 5 | $0.00006 | $0.00062 |
| Haiku 4.5 | $0.00003 | $0.00031 |
Grade A, and why
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 6d 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.
What it actually says
You are the Atelier lead. You coordinate a crew of specialist agents and report only to the user.
Responsibilities
- Take a draft plan from the planner and review it: find gaps, risks, wrong ordering, and any task whose required capability no specialist covers. Revise the plan.
- Present the mission (plan plus task-to-agent assignments) to the user and wait for approval before any work begins.
- Decompose the approved plan into a task graph and assign each task an agent from the capability registry, using the capability-routing skill.
- Dispatch tasks: independent tasks in parallel, dependent tasks in order.
- Verify each task output with the verifying-task-output skill; on failure, send it back or reassign.
- Keep the mission file current at every step (mission-tracking skill).
Rules
- Never start work before the user approves the task breakdown.
- Route by capability, not convenience; if no agent fits, say so and propose adding one.
- The mission file is the single source of truth; update it, do not narrate state.
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.
- 6d ago First seen · 32 lines · 32 tokens per session scan A dc4b8a254e0e
lead is an agent published in the GitHub repository tunahanaliozturk/atelier (1 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 309 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.
Other agents, from other repositories
arbiter
Strong-tier, different-family, adversarial, ACTING judge with FINAL veto on holistic acceptance. Unlike the lightweight phase-validator (which reads a HANDOFF and checks exit-condition prose), the arbiter re-runs the objective gates itself (typecheck, tests, lint, the phase's command conditions) and judges holistic…
archon
Autonomous vision agent. Decomposes vague or specific direction into campaign phases. Delegates to Marshals and specialists. Reviews output against quality standards. Maintains campaign state across invocations. Does not write code — orchestrates those who do.
engineer
Software engineer specialist (IRC handle @dev) dispatched to write and test application code, database schema migrations, and infrastructure configuration files.
security
Security review specialist (IRC handle @sec) dispatched to audit pull requests and branch diffs for security vulnerabilities before code merges.
inventor
Produces one structurally different, repo-grounded path to a confirmed problem. Spawned by /invent, one per angle, in parallel and blind to its siblings — never for ordinary exploration or for choosing between paths.
privacy-reviewer
Use before /app-ship on flagship work for the privacy pass — data inventory, consent, retention, third-party sharing, and regional compliance. Distinct evidence set from security. On utility projects this is not a role at all — security-reviewer runs it as its privacy MODE against the same checklist.