Borrowing it
Nothing to install: this file belongs to PostHog/posthog-foss. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/PostHog/posthog-foss/master/.agents/skills/qa-team/SKILL.mdgit clone --depth 1 https://github.com/PostHog/posthog-fossWrote 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/posthog/posthog-foss/qa-team)<a href="https://agentmods.dev/skills/posthog/posthog-foss/qa-team"><img src="https://agentmods.dev/badge/skills/posthog/posthog-foss/qa-team.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 3 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- high Data Exfiltration · line 32 Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
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 | $0.00110 | $0.04140 |
| Opus 5 | $0.00055 | $0.02070 |
| Sonnet 5 | $0.00022 | $0.00828 |
| Haiku 4.5 | $0.00011 | $0.00414 |
Grade C, and why
qa-team scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
After the report is written, best-effort clean up the run directory (`rm -rf "$RUN_DIR"`) How it starts
The opening of the file, as written. The whole thing — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Team: Multi-Agent Code Review
A team of specialist agents independently review the current branch's changes against real incident patterns. Their findings are synthesized into a single report with convergence analysis.
Agent independence is critical. Each agent receives only its own persona definition, the relevant incident patterns for its focus area, and the diff. Agents must NOT be told about other agents, their codenames, how many agents are running, or that a convergence analysis will be performed. This ensures findings are fully independent.
Workflow
Step 1: Gather the diff
Determine the base branch. If the user provided $ARGUMENTS, use that as the base branch.
Otherwise, default to master.
Create a run directory outside the repository (session scratchpad or mktemp -d — never
inside the repo), then collect context into it:
RUN_DIR="$(mktemp -d "${TMPDIR:-/tmp}/qa-team-XXXXXX")"
mkdir -p "$RUN_DIR/personas" "$RUN_DIR/claimed"
git diff <base>...HEAD --name-only > "$RUN_DIR/files.txt"
git log <base>...HEAD --oneline > "$RUN_DIR/commits.txt"
git diff <base>...HEAD > "$RUN_DIR/diff.patch"
The run directory holds the persona queue, the claim script, and the generated launch
scripts (Step 3); the diff is baked into the shared agent prompt by the build script,
without passing through the model (see Step 3 for why). Keep diff.patch on disk — the
build script reads it, and oversized diffs fall back to it at review time.
If there are no changes, inform the user and stop.
Step 2: Classify changed files
Categorize changed files to determine which agents are relevant:
| File pattern | Relevant agents |
|---|---|
*.py (migrations) |
database, reliability, compatibility |
*.py (Django views/API) |
security, reliability, performance, data-integrity |
*.py (Celery tasks) |
reliability, performance, data-integrity |
*.rs (Rust services) |
security, performance, compatibility, reliability |
*.tsx, *.ts (frontend) |
frontend, security, performance, copy |
*.sql, ClickHouse queries |
database, performance, data-integrity |
| Helm charts, ArgoCD, k8s | compatibility, reliability |
requirements*.txt, pyproject.toml, package.json |
security, compatibility |
| SDK/extension code | compatibility, frontend, security, copy |
| Any file with user-facing strings | copy |
| GitHub Actions workflows | security |
What ships with it
4 files 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.
- 7d ago First seen · 365 lines · 110 tokens per session scan C dbfb15282b76
qa-team is a skill published in the GitHub repository PostHog/posthog-foss (714 stars, last pushed today), licensed MIT. It adds 110 tokens to every session and 4,140 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
semgrep-rule-variant-creator
Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.