posthog-foss: Skill for Claude Code

.agents/skills/qa-team/SKILL.md

qa-team is a skill for Claude Code from PostHog/posthog-foss. It costs 110 tokens per session (4,140 once invoked), scanned C, original, MIT.

A multi-agent code review process in which several independent reviewers examine the changes on your current Git branch and combine their findings into one report.

In plain words
What is it for?
Use it to review a branch, check recent code changes, or run a broad quality check before merging.
Why use it?
It reduces the chance that one reviewer misses a bug or risk by checking the same changes from several specialist viewpoints.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: installed under .agents/ (shared by several agents).

This is PostHog/posthog-foss's own configuration. It tells Claude Code how to work on posthog-foss itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything posthog-foss configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/PostHog/posthog-foss/master/.agents/skills/qa-team/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/PostHog/posthog-foss

Made for: Claude Code.

Wrote 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.

agentmods badge for qa-team

README.md
[![agentmods](https://agentmods.dev/badge/skills/posthog/posthog-foss/qa-team.svg)](https://agentmods.dev/skills/posthog/posthog-foss/qa-team)
Your own site
<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>
Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,140 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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.
How audits are shown
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 5.1 $0.00110 $0.04140
Opus 5 $0.00055 $0.02070
Sonnet 5 $0.00022 $0.00828
Haiku 4.5 $0.00011 $0.00414

Measured 7d ago against content hash dbfb15282b76, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/build_launch_scripts.js, scripts/claim_persona.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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"`)
.agents/skills/qa-team/SKILL.md · 365 lines

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

Read the full file on GitHub · 365 lines

Files

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.

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. 7d ago First seen · 365 lines · 110 tokens per session scan C dbfb15282b76

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories