qualification

A qualification guide that reads signals from a user's request and background context to decide how much effort to invest and which response approach fits. It considers factors such as business stakes, decision-making ability, engagement, and practical scope.

In plain words
What is it for?
Use it during the first substantive interaction to assess the request, choose an appropriate working mode, and decide whether to continue normally or redirect.
Why use it?
It helps an agent tailor its response to the user's situation instead of using the same approach for every request.

Skill for Claude CodeCodex

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 skills/quantumbyteoss/quantumbyte/qualification
Any agent
npx skills add QuantumByteOSS/quantumbyte --skill qualification
Clone the repo
git clone --depth 1 https://github.com/QuantumByteOSS/quantumbyte

Made for: Claude Code, Codex.

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 579 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original 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 $0.00066 $0.00579
Opus 5 $0.00033 $0.00290
Sonnet 5 $0.00013 $0.00116
Haiku 4.5 $0.00007 $0.00058

Measured yesterday against content hash c090cc2b8bbd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qualification 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 yesterday.

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.

apps/worker/shared/prompts/agents/main_agent/skills/qualification/SKILL.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Qualification

A parallel read, not a gate the user sees. It answers two questions: should we invest here, and which vacation do we sell?

Signals (from input + passive context)

  • real_business — a concrete operation, not a vague idea.
  • stakes — money, time, or reputation on the line.
  • agency — can this person actually decide / act?
  • engagement — specifics vs hand-waving.
  • realism — is this in QB's wheelhouse (operational/service apps), not a consumer-megascale fantasy?

Combine into a Magnet magnitude (low / medium / high) — Magnet is the dream's pull, the force qualification reads first. High Magnet → effort_mode: double_down. Low → light touch or route to disqualification. A realism failure caps the whole thing regardless of Magnet — the forces are multiplicative (see the system prompt).

Archetype (drives which vacation, and how the bears behave)

Archetype Tell Vacation to sell Bear posture
Solo founder own checkbook, runs the thing reclaim time / stop the bleed practical, plainspoken
Champion in-org advocate, needs sign-off look good to leadership; load their pitch ROI-framed; draft the internal case
Hobbyist no commercial pressure the joy of the thing shipped peer-to-peer, honest about scope
Economic buyer signs the check directly risk-down, clear ROI crisp, numbers-first

Default to neutral if the archetype flag is absent — never force a label on thin evidence.

Routing

  • magnitude ≥ minimum → proceed; pass archetype + effort_mode to the spine so the convince ladder is tuned.
  • magnitude sustained-low OR realism failure → hand to disqualification.

The cost of skipping qualification

If the user skips ahead (or the opening loop didn't gather enough), proceed at neutral effort — but know the convince ladder and the generated app will be generic. That's the visible cost of a thin read; it's acceptable, not ideal.

Dependencies (fall back if absent)

Read the full file on GitHub · 43 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. yesterday First seen · 43 lines · 66 tokens per session scan A c090cc2b8bbd

Subscribe to this mod's changes

qualification is a skill published in the GitHub repository QuantumByteOSS/quantumbyte (323 stars, last pushed 19d ago), licensed Apache-2.0. It adds 66 tokens to every session and 579 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 2026-08-30.

Related

Other skills, from other repositories

gsd

Get Shit Done (GSD) - A comprehensive project management system for solo developers using Claude agents.

allgpt-co/QuickVoice · 23 tokens

st-full-workflow

Use when the user asks to run the complete end-to-end Strikethroo workflow for a work order in one shot in this repository — triggers include full workflow, end-to-end, plan and execute, do everything, run the whole strikethroo workflow. Do not use when the user wants only one stage (create a plan, generate tasks, or…

e0ipso/strikethroo · 90 tokens

st-execute-blueprint

Use when the user asks to run, execute, implement, or carry out a Strikethroo plan or its blueprint by plan ID in this repository — triggers include execute blueprint, run the plan, implement plan, build the plan. Do not use to create a plan, to only generate tasks, to run a single task, or for generic development…

e0ipso/strikethroo · 82 tokens

st-generate-tasks

Use when the user asks to decompose, break down, or generate tasks for an existing Strikethroo plan ID in this repository — triggers include generate tasks, break down the plan, decompose plan, create the task blueprint. Do not use to create a new plan, to execute tasks, or for generic project planning outside…

e0ipso/strikethroo · 77 tokens

st-code-review

Use when the blueprint execution gate asks for an independent second-harness review of a Strikethroo plan's cumulative diff in this repository — triggers include code review gate, review the plan diff, second-model review, CODEREVIEW hook, review the cumulative diff. Do not use to review a single task, to review code…

e0ipso/strikethroo · 87 tokens

st-execute-task

Use when the user asks to run, execute, or implement one specific task ID within a Strikethroo plan in this repository — triggers include execute task, run task, implement task, do task N. Do not use to execute a whole plan or blueprint, to generate tasks, or for generic development outside Strikethroo.

e0ipso/strikethroo · 72 tokens