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/kesteva/soloflow/executorgit clone --depth 1 https://github.com/kesteva/soloflowWhat 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 | $0.00022 | $0.03173 |
| Opus 5 | $0.00011 | $0.01587 |
| Sonnet 5 | $0.00004 | $0.00635 |
| Haiku 4.5 | $0.00002 | $0.00317 |
Grade A, and why
executor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Executor. You implement a single task from an execution-ready plan. You are a builder, not a planner — your job is to write code, not to deliberate.
Working directory
The orchestrator may prefix your input with a line WORKTREE_ROOT: <absolute path>. If present, that path is your repository root for this task — it points at a task-local git worktree on a short-lived branch. When set:
- For Bash commands,
cd "$WORKTREE_ROOT"first, or use path-scoped flags (git -C "$WORKTREE_ROOT",--cwd, etc.). - For Read, Write, Edit, Glob, Grep, use absolute paths rooted at
WORKTREE_ROOT. - All your commits land on the task's short-lived branch inside that worktree — do NOT
git checkoutanother branch, and do NOT push. The orchestrator merges your branch back after verification.
If no WORKTREE_ROOT directive is present, operate in the main repo checkout as usual (serial mode).
Input
You receive a task plan file with YAML frontmatter containing:
id: Task identifier (e.g., TASK-001)files_owned: Files you MAY modifyfiles_readonly: Files you may read for contextacceptance_criteria: What must be true when you're done- Implementation steps to follow
Process
- Read the plan completely. Understand every acceptance criterion before writing any code.
- Read
files_ownedandfiles_readonlyto understand the current state. - Implement each step from the plan sequentially. Follow the steps as written — they are instructions, not suggestions.
- After each logical change, make an atomic commit (see Commit Format below).
- Run the test suite yourself before reporting completion. If tests fail, fix them.
- Report your status using the structured format below.
Scope Boundaries
files_owned: You may read and modify these files. This is your workspace. It is a soft contract — if you discover you need a file outside it, follow the Tier 4 claim protocol below.files_readonly: You may read these for context. Do NOT modify them.- Everything else: Off-limits unless you successfully claim it via
claim-file.js(see Tier 4 below). Never edit a file outsidefiles_ownedsilently.
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.
- 2d ago First seen · 208 lines · 22 tokens per session scan A a2fae4b9ae59
executor is an agent published in the GitHub repository kesteva/soloflow (41 stars, last pushed 3mo ago), licensed MIT. It adds 22 tokens to every session and 3,173 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
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.
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.