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 skills/ldbumble/taskuary/soul-interviewnpx skills add ldbumble/taskuary --skill soul-interviewgit clone --depth 1 https://github.com/ldbumble/taskuaryWrote 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/ldbumble/taskuary/soul-interview)<a href="https://agentmods.dev/skills/ldbumble/taskuary/soul-interview"><img src="https://agentmods.dev/badge/skills/ldbumble/taskuary/soul-interview.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 | $0.00044 | $0.01150 |
| Opus 5 | $0.00022 | $0.00575 |
| Sonnet 5 | $0.00009 | $0.00230 |
| Haiku 4.5 | $0.00004 | $0.00115 |
Grade A, and why
soul-interview 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.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adaptive SOUL.md interview
Learn how the assistant should work for this particular person. Do not assume their work is technical, office-based, managerial, or connected to software.
Fixed product boundaries are not interview topics
Taskuary's approval gate is a system rule, not a preference SOUL.md can grant or relax. Nothing is sent, posted, published, shipped, or otherwise put in front of another person without the owner's explicit approval. Never ask the owner which outbound actions may bypass approval, never offer examples of exceptions, and never turn an interview answer into such permission. The interview may ask what research, organization, analysis, or drafting would be useful before the owner decides; it must not ask what Taskuary may send or ship on its own.
Do not ask broad permission questions such as "what may I change or commit without asking?" The agent and playbook rules govern execution. SOUL.md should instead explain what matters, what the assistant should notice, how it should communicate, and which ambiguities deserve the owner's judgment.
Interview
- Ask exactly seven user-facing questions, one at a time. Wait for each answer before choosing the next question.
- Start broad: ask what the person wants the assistant to understand about them and the world in which they work. The first answer establishes the vocabulary and direction for the interview.
- Generate questions 2–7 from the full transcript so far. Refer naturally to useful specifics from earlier answers and pursue the highest-value missing detail. A generic fixed sequence is not adaptive.
- Ask one clear question per turn. Do not hide several unrelated questions in one sentence.
- Never ask specifically about code, repositories, infrastructure, or software unless the person introduced that subject. Use their domain's language instead.
- Respect “skip”, uncertainty, and short answers. Do not manufacture facts or pressure the person.
- Across the seven answers, learn enough to describe the person's context and desired outcomes, what matters most and what deserves attention, how the assistant should communicate and summarize, which ambiguities need the person's judgment, the person's organizational relationships, and the tools or sources of truth that shape the work. These are coverage goals, not a questionnaire: combine, reorder, or replace them when the conversation makes another follow-up more valuable.
- Do not repeat a fact already answered unless the answer exposed a consequential ambiguity.
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.
- today Changed · +35 lines 59126e91cbee
- yesterday First seen · 58 lines · 44 tokens per session scan A bb89949e8952
soul-interview is a skill published in the GitHub repository ldbumble/taskuary (45 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 1,150 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 2026-09-04.
Other skills, from other repositories
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
worker-integration
Worker-Agent integration for intelligent task dispatch and performance tracking.
agui-dotnet-streaming-chat
Get started with the AG-UI .NET SDK: bootstrap and run your first streaming-chat app (client + server) with the AG-UI .NET NuGet packages (AGUI.Client, AGUI.Server, AGUI.Formatting, AGUI.Abstractions). USE FOR: which packages to install and how to wire them; constructing an AGUIChatClient against an endpoint and…
agui-dotnet-sample-step
Add a GettingStarted sample Step (a Server/Client pair) to the AG-UI .NET SDK that demonstrates one protocol feature the way we want users to write it. USE FOR: adding a new samples/GettingStarted/StepNN Server+Client pair, wiring it into AGUI.slnx and the integration-test project, giving it a deterministic…
agui-dotnet-protobuf
Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…
cog-knowledge-consolidation
Build structured knowledge frameworks from scattered vault notes with source attribution.