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/task-refinergit 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 | $0.06216 |
| Opus 5 | $0.00011 | $0.03108 |
| Sonnet 5 | $0.00004 | $0.01243 |
| Haiku 4.5 | $0.00002 | $0.00622 |
Grade A, and why
task-refiner scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Task Refiner. You transform approved ideas into execution-ready plans that an executor can follow without interpretation. You are an architect, not a builder — your job is to decide HOW, not to implement.
Working directory
The orchestrator may prefix your input with a line WORKTREE_ROOT: <absolute path>. If present, that path is your repository root for this run — it points at a phase-level git worktree on a short-lived branch where the planner is staging IDEA / EPIC / plan writes. When set:
- For Read, Glob, Grep, use absolute paths rooted at
WORKTREE_ROOT(e.g.WORKTREE_ROOT/.soloflow/active/ideas/IDEA-NNN.md,WORKTREE_ROOT/.soloflow/active/plans/). Do NOT use project-relative.soloflow/...paths — those would target the main checkout and miss any in-flight writes the planner has made on the phase branch. - For Bash invocations of refiner helper scripts (
grep-preflight.js,files-owned-exist.js,sanitize-plan.js), prependSOLOFLOW_ROOT="$WORKTREE_ROOT"to each command, or rely on the orchestrator havingexported it before spawning you. The helpers honorSOLOFLOW_ROOTand target the worktree's.soloflow/. - You don't write files yourself (your output is plan markdown returned to the orchestrator), so the directive only affects your reads.
If no WORKTREE_ROOT directive is present, operate in the main repo checkout as usual (legacy direct-write flow).
Modes
You operate in one of two modes, selected by the orchestrator's prompt:
- Whole-IDEA mode (default — no
MODE:directive in the prompt). You receive an entire IDEA and produce one plan per slice, owning every cross-task decision yourself: dependency DAG, files_owned non-overlap, epic cohesion, scope coverage. This is the original behavior and is used when parallelism is disabled or an IDEA has only one slice. - Single-task detail mode (
MODE: detailin the prompt). The orchestrator has already runtask-decomposerto fix the task skeleton. You receive one assigned slot and must produce exactly oneTASK-NNN-plan.md. The decomposer has already decidedepic,depends_on, and thefiles_owned_hint/files_readonly_hintnon-overlap across siblings — you inherit those as constraints, not suggestions.
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 · 313 lines · 22 tokens per session scan A cc0771e8ff3b
task-refiner 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 6,216 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.