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 skills add softspark/ai-toolkit --skill qa-sessiongit clone --depth 1 https://github.com/softspark/ai-toolkitWrote 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/softspark/ai-toolkit/qa-session)<a href="https://agentmods.dev/skills/softspark/ai-toolkit/qa-session"><img src="https://agentmods.dev/badge/skills/softspark/ai-toolkit/qa-session/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/softspark/ai-toolkit/qa-session"><img src="https://agentmods.dev/badge/skills/softspark/ai-toolkit/qa-session.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00036 | $0.01102 |
| Opus 5 | $0.00018 | $0.00551 |
| Sonnet 5 | $0.00007 | $0.00220 |
| Haiku 4.5 | $0.00004 | $0.00110 |
Grade A, and why
qa-session 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 6d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Session
$ARGUMENTS
Interactive QA session. User describes problems, agent clarifies, explores codebase, and files GitHub issues.
Usage
/qa-session [area to QA or first bug report]
What This Command Does
- Listens to user's bug report
- Clarifies with 2-3 focused questions max
- Explores codebase in background for context and domain language
- Assesses scope — single issue or breakdown
- Files GitHub issues via
gh issue create - Continues until user says done
For Each Issue
1. Listen and Lightly Clarify
Let user describe the problem. Ask at most 2-3 short questions on:
- Expected vs actual behavior
- Steps to reproduce
- Consistent or intermittent
Don't over-interview. If clear enough, move on.
2. Explore Codebase in Background
Kick off Agent (subagent_type=Explore) in background to:
- Learn domain language (check UBIQUITOUS_LANGUAGE.md)
- Understand what the feature should do
- Identify behavior boundaries
This helps write better issues — but issues must NOT reference files/lines.
3. Assess Scope
| Decision | When |
|---|---|
| Single issue | One behavior wrong in one place |
| Breakdown | Multiple independent areas, separable concerns, distinct failure modes |
4. File GitHub Issues
Use gh issue create. Do NOT ask to review — file and share URLs.
Single issue template:
## What happened
[Actual behavior in plain language]
## What I expected
[Expected behavior]
## Steps to reproduce
1. [Concrete numbered steps]
2. [Use domain terms, not module names]
## Additional context
[Extra observations using domain language]
Breakdown template (for each sub-issue):
## Parent issue
#{parent-issue-number} or "Reported during QA session"
## What's wrong
[This specific behavior problem]
## What I expected
[Expected behavior for this slice]
## Steps to reproduce
1. [Steps specific to THIS issue]
## Blocked by
- #{issue-number} or "None — can start immediately"
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.
- 6d ago First seen · 127 lines · 36 tokens per session scan A 80fd4b5c6d63
qa-session is a skill published in the GitHub repository softspark/ai-toolkit (170 stars, last pushed yesterday), licensed Apache-2.0. It adds 36 tokens to every session and 1,102 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 2026-09-03.
Other skills, from other repositories
escalation
Structure and package support escalations for engineering, product, or leadership with full context, reproduction steps, and business impact. Use when an issue needs to go beyond support, when writing an escalation brief, or when assessing whether an issue warrants escalation.
cline-fix-volatile-msg
Ladder-aware Cline Anthropic caching — verify the rolling read/write ladder on the wire, then add the tools breakpoint and tune TTL. Updated for the 2026-08 AI-SDK monorepo.
cline-pin-timestamp
Cline's system prompt includes a timestamp that may be recomputed per request, invalidating the system-prompt cache.
continue-fix-volatile-msg
Ladder-aware Continue Anthropic caching — verify the rolling ladder on the wire, then enable it by default and add TTL coverage.
opencode-detect-openai-compat
OpenCode's caching detection misses OpenAI-compatible proxies routing to Anthropic/Bedrock. Broaden the predicate.
bug-triage
Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic trends, and produce a triage report. Run at sprint start or when the bug count grows enough to need re-prioritization.