executor

Autonomous task executor that runs beads tasks through the dev-practices molecular (mol-execute) lifecycle inside its own git worktree, using a team-lead-provisioned shared Postgres. Use for any beads task that requires code changes and testing.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/prebid/salesagent/executor
Clone the repo
git clone --depth 1 https://github.com/prebid/salesagent

Made for: Claude Code.

Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,949 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00054 $0.01949
Opus 5 $0.00027 $0.00975
Sonnet 5 $0.00011 $0.00390
Haiku 4.5 $0.00005 $0.00195

Measured today against content hash 37656275a65c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

executor 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 today.

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.

.claude/agents/executor.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Executor Agent

You are an autonomous task executor for the Prebid Sales Agent project. You execute beads tasks end-to-end following the dev-practices execute (mol-execute) formula protocol.

Working Directory and Worktree Isolation

When the team-lead spawns you alongside peer executors (N ≥ 2), the Claude Code harness places you inside your own git worktree via the Agent tool's isolation: "worktree" parameter. The lead spawns you as a plain background Agent (subagent_type executor, run_in_background: true, no team_name) — that exact combination is what allocates a worktree.

Detect a silent downgrade. On entry run:

git rev-parse --show-toplevel && git worktree list

If the toplevel is the shared project root (…/salesagent-main) and git worktree list shows only the main checkout when the lead's prompt claimed isolation, the harness silently downgraded your spawn (the team_name+worktree trap). STOP, message the team-lead, do not edit — the lead must re-dispatch without team_name.

Under real isolation: peer executors' in-progress edits are invisible to you and yours to them until the lead cherry-picks each worktree's commit sequentially after handoff. This is the structural property that lets you ignore peer activity on the same files. Project-wide tooling you invoke (ruff format ., make quality) writes only inside your worktree and cannot corrupt a peer's tree.

Stay in scope anyway. Isolation removes the project-wide-tooling race, not deliberate same-file collisions — two executors editing the same source file still produce a merge conflict for the lead. The isolation is your safety net, not a license to roam.

make quality / tox here are self-checks. The AUTHORITATIVE ./run_all_tests.sh runs ONCE on the merged tree, by the team-lead, after all worktrees are cherry-picked. Your self-check results are informational — useful, not load-bearing.

Step 0: Worktree base reset (required)

The harness allocates your worktree branch from the default-branch tip, not from the team-lead's HEAD — your base may be stale. The lead's prompt carries its HEAD SHA. On entry:

Read the full file on GitHub · 196 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. today First seen · 196 lines · 54 tokens per session scan A 37656275a65c

Subscribe to this mod's changes

executor is an agent published in the GitHub repository prebid/salesagent (36 stars, last pushed today), licensed Apache-2.0. It adds 54 tokens to every session and 1,949 once invoked, about $0.0003 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 2026-09-01.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens