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 TimothyHan/qa-buddy-skills --skill setupgit clone --depth 1 https://github.com/TimothyHan/qa-buddy-skillsWrote 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/timothyhan/qa-buddy-skills/setup)<a href="https://agentmods.dev/skills/timothyhan/qa-buddy-skills/setup"><img src="https://agentmods.dev/badge/skills/timothyhan/qa-buddy-skills/setup/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/timothyhan/qa-buddy-skills/setup"><img src="https://agentmods.dev/badge/skills/timothyhan/qa-buddy-skills/setup.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00096 | $0.02069 |
| Opus 5.5 | $0.00038 | $0.00828 |
| Sonnet 5.5 | $0.00019 | $0.00414 |
| Haiku 4.5 | $0.00010 | $0.00207 |
Grade B, and why
setup scanned grade B with 1 finding 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 27d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
grep -r "atlassian" ~/.claude/settings.json .claude/settings.json .claude/settings.local.json 2>/dev/null How it starts
The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/qa-setup: QABuddy Configuration
Configure QABuddy for this project. Creates .qabuddy.json at the project root
with your preferences. All other skills read this config to adjust their behavior.
Constraints
- Never overwrite without asking. If
.qabuddy.jsonexists, show current config first. - Verify before saving. Show the full config and confirm before writing the file.
- One question at a time. Don't batch questions.
Phase 1: Check Existing Config
cat .qabuddy.json 2>/dev/null
- If config exists: Show it and ask: "Want to reconfigure or keep current settings?"
- (A) Reconfigure — proceed to Phase 2
- (B) Keep — show summary and exit
- If no config: Proceed to Phase 2
Phase 2: Context Source
Ask the SDT:
"How does your team provide feature context (epic details, acceptance criteria, specs)?"
- (A) Jira (recommended if using Atlassian) — I'll query tickets via Atlassian MCP
- (B) Specification documents — feature specs live as files in this repo (e.g.,
docs/,specs/) - (C) Chat — you'll paste or link context when needed
- (D) Custom — describe your method
If Jira: Ask for the project key (e.g., "PROJ"). Verify Jira MCP connectivity:
# Check if atlassian MCP is configured
grep -r "atlassian" ~/.claude/settings.json .claude/settings.json .claude/settings.local.json 2>/dev/null
If MCP not found, warn but don't block — SDT can set it up later.
Features and stories use Jira keys as KB identifiers (e.g., PROJ-123, PROJ-456).
If Spec, Chat, or Custom: Explain naming:
"Since you're not using Jira, you'll name features and stories yourself when running skills.
Use short, descriptive slugs (e.g., auth-system, login-page, pdf-export).
These become directory names in the knowledge base:
features-kb/features/auth-system/test-cases/login-page.md"
If Custom: Also ask for a brief description of the method (stored in config).
Phase 3: Team Mode
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 27d ago Changed · -66 lines · -20 tokens per session a5d61985fd9f
- 1mo ago Changed · +67 lines · +20 tokens per session 855a85f325ac
- 1mo ago First seen · 219 lines · 96 tokens per session scan B b50d65f1062d
setup is a skill published in the GitHub repository TimothyHan/qa-buddy-skills (9 stars, last pushed 19d ago), licensed Apache-2.0. It adds 96 tokens to every session and 2,069 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
Honesty Check
Run the volunteering ledger before declaring work done. Forces surfacing of what changed/didn't, what was noticed-but-not-fixed, what was guessed, and what tradeoffs were made on the principal's behalf. The standard - the principal should never be surprised later by something the agent knew at the time.
Envelope
Classify any incoming directive as Ship / Ask one focused question / Propose first. Forces a sharp decision instead of a multi-option survey to the principal. The default failure mode for agents is treating ship-work as ask-work (over-surveying) or treating propose-work as ship-work (rushing irreversible changes).…
nightly-ledger-capture
Discovers missing honesty, trust-decay, failure-mode, and decision-outcome entries from local evidence; stages judgment and permits direct mutation only after an executable oracle.
reconcile
Read-only attention reconciliation. Computes actual seven-day project attention from daily notes against explicit Tier-1 intended shares.
bug-report
A guided process for creating a bug report in Jira, a tool for tracking software work and defects.
sweep-tracker
Hestia's delegation tracker sweep skill. Reads DELEGATIONTRACKER.md, closes finished items, archives stale items beyond threshold, flags orphaned items. Returns counts. Edit-only on status fields.