quality-gate

A generator for a Stop hook that checks whether a project passes its available code-quality checks before the agent finishes. It selects checks such as TypeScript type checking, Rust checking, Go vetting, Python type checking, or JavaScript linting.

In plain words
What is it for?
Use it to add a quality gate to a project and block completion when its configured checker reports errors.
Why use it?
It can prevent the agent from declaring the work finished while the code still has detectable problems. It also avoids repeatedly triggering itself in a loop.

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/sliday/harn/quality-gate
Any agent
npx skills add sliday/harn --skill quality-gate
Clone the repo
git clone --depth 1 https://github.com/sliday/harn

Made for: Claude Code, Codex.

Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 963 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 $0.00039 $0.00963
Opus 5 $0.00019 $0.00481
Sonnet 5 $0.00008 $0.00193
Haiku 4.5 $0.00004 $0.00096

Measured 2d ago against content hash d048c0636770, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

quality-gate 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 2d 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.

skills/quality-gate/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quality Gate Generator

Generate or update scripts/harness/quality_gate.sh for the current project.

Process

  1. Detect the project's tech stack
  2. Select appropriate checker(s):
    • TypeScript → npx tsc --noEmit
    • Rust → cargo check
    • Go → go vet ./...
    • Python → mypy or pyright
    • JavaScript → npx eslint .
  3. Generate the quality gate script with infinite-loop prevention
  4. Ensure it's wired as a Stop hook in .claude/settings.json

Key Requirements

  • MUST check stop_hook_active payload to prevent infinite loops
  • MUST output errors to stderr (fed back to agent)
  • MUST exit 2 to block, exit 0 to allow
  • Should complete in under 30 seconds

Generated Script Template

The generated scripts/harness/quality_gate.sh must include the following robustness patterns:

KB References (at top of script)

# Harn quality gate — blocks agent completion if code is broken
# Why: https://harn.app/kb/safety.html — "Quality checks in the loop"
# Pattern: https://harn.app/kb/evals.html — "Infrastructure noise moves benchmarks"

Dependency Checks (before any checker runs)

command -v jq &>/dev/null || { echo "Harn: jq not found, quality gate skipped" >&2; exit 0; }

Session-Aware Temp File (replaces /tmp/harn_gate.log)

LOG_FILE="${TMPDIR:-/tmp}/harn_gate_${PPID}_$$.log"

Checker Guards (verify tool exists before running)

Each checker must be guarded with command -v before invocation:

if [ -f "tsconfig.json" ]; then
  command -v npx &>/dev/null || {
    echo "QUALITY GATE BLOCKED: TypeScript detected but 'npx' not found." >&2
    echo "Install Node.js or remove tsconfig.json." >&2
    exit 2
  }
  npx tsc --noEmit > "$LOG_FILE" 2>&1 || {
    echo "QUALITY GATE BLOCKED: TypeScript errors found:" >&2
    cat "$LOG_FILE" >&2
    exit 2
  }
fi

if [ -f "Cargo.toml" ]; then
  command -v cargo &>/dev/null || {
    echo "QUALITY GATE BLOCKED: Rust detected but 'cargo' not found." >&2
    echo "Install Rust toolchain or remove Cargo.toml." >&2
    exit 2
  }
  cargo check > "$LOG_FILE" 2>&1 || {
    echo "QUALITY GATE BLOCKED: Cargo check errors found:" >&2
    cat "$LOG_FILE" >&2
    exit 2
  }
fi

if [ -f "go.mod" ]; then
  command -v go &>/dev/null || {
    echo "QUALITY GATE BLOCKED: Go detected but 'go' not found." >&2
    echo "Install Go or remove go.mod." >&2
    exit 2
  }
  go vet ./... > "$LOG_FILE" 2>&1 || {
    echo "QUALITY GATE BLOCKED: Go vet errors found:" >&2
    cat "$LOG_FILE" >&2
    exit 2
  }
fi

if [ -f "mypy.ini" ] || [ -f "setup.cfg" ] || [ -f "pyproject.toml" ]; then
  command -v mypy &>/dev/null || {
    echo "QUALITY GATE BLOCKED: Python type checking configured but 'mypy' not found." >&2
    echo "Install mypy or remove type checking config." >&2
    exit 2
  }
  mypy . > "$LOG_FILE" 2>&1 || {
    echo "QUALITY GATE BLOCKED: mypy errors found:" >&2
    cat "$LOG_FILE" >&2
    exit 2
  }
fi

Read the full file on GitHub · 115 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. 2d ago First seen · 115 lines · 39 tokens per session scan A d048c0636770

Subscribe to this mod's changes

quality-gate is a skill published in the GitHub repository sliday/harn (5 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 963 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens