Repository rules for choosing and reporting verification commands after changes.

They define checks such as whitespace validation, shell syntax checks, scaffold dry runs, status inspection, and workflow-specific verification.

They keep checking focused on the changed area and prevent work from advancing when validation fails or required tools are assumed to exist.

execution — Cursor rule by kyungseo

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 rules/kyungseo/ai-workflow-harness/execution

Clone the repo

git clone --depth 1 https://github.com/kyungseo/ai-workflow-harness

Made for: Cursor.

Per session 349 This file is loaded in full into every session.

When invoked 349 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5	$0.00349	$0.00349
Opus 5	$0.00175	$0.00175
Sonnet 5	$0.00070	$0.00070
Haiku 4.5	$0.00035	$0.00035

Measured 2d ago against content hash 75f5f8211dbe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

execution 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.

.cursor/rules/execution.mdc · 42 lines

What it actually says

Execution Rules

Default verification commands:

git diff --check
bash -n scripts/create-harness.sh
./scripts/create-harness.sh --dry-run --profile generic <name> <target-dir>

MUST:

Choose the narrowest verification command that proves the change.
Report any command you could not run and why.
Check the Active Work pointer in docs/STATUS.md and the target Work file's Verification/Checkpoints before broader validation.
Follow any verification scope defined in the active plan or relevant backlog.
Use docs/backlog/HARNESS.md for harness/workflow verification scope.
Treat failed verification as FAIL -> RECOVER -> PLAN; do not proceed to checkpoint until the failure is reported and resolved or explicitly accepted.

NEVER:

Run destructive commands without explicit approval.
Run privileged commands.
Assume a Java, Gradle, Docker, database, or application runtime exists in this repository.
Use alternate build tools unless the repository explicitly requires them.

CI Trigger Structure

pull_request targeting main or develop: docs, prompts, tool rules, scaffold, and workflow changes run lightweight validation.
push to main: same lightweight validation for release-bound changes.
develop branch push: no CI trigger unless explicitly added later.

Verification Commands

git diff --check — whitespace and patch hygiene
bash -n scripts/create-harness.sh — scaffold shell syntax
./scripts/create-harness.sh --dry-run --profile generic sample /tmp/sample — generic scaffold plan check

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.

2d ago First seen · 42 lines · 349 tokens per session scan A 75f5f8211dbe

Subscribe to this mod's changes

execution is a cursor rule published in the GitHub repository kyungseo/ai-workflow-harness (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 349 tokens to every session, about $0.0017 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 2026-08-30.

Productivity agentic-ai ai-workflow claude-code codex cursor developer-tools

language-agnostic-patterns

Language-agnostic programming patterns: SOLID, design patterns, clean code, and architecture. Load when refactoring, designing abstractions, or reviewing structure — not for everyday syntax.

madebyaris/advance-minimax-m3-cursor-rules · 37 tokens

cursor-tools-mastery

Cursor 3.7 runtime guide: choose the right tool, canvases, Design Mode, /worktree, /best-of-n, Await, and parallel execution where safe.

madebyaris/advance-minimax-m3-cursor-rules · 36 tokens

fable5-coding-craft

Fable 5 coding craft: locate-before-write, root-cause method, simplicity taste, error-handling philosophy, test integrity, refactoring discipline, and counters to common LLM coding failure modes. Load when writing, refactoring, debugging, or reviewing non-trivial code in any language.

madebyaris/advance-minimax-m3-cursor-rules · 60 tokens

cursor-agent-orchestration

Cursor 3.7 orchestration guide: when to plan, when to delegate, nested subagents, multi-environment handoffs, /best-of-n, and Await for long-running branches.

madebyaris/advance-minimax-m3-cursor-rules · 39 tokens

fable5-reasoning

Fable 5 reasoning protocols: task interpretation, risk-first decomposition, approach selection, interleaved thinking, hypothesis ledgers, premortems, calibration, and the stuck-strategy ladder. Load for complex, ambiguous, or long-horizon tasks, for debugging strategy, or whenever progress stalls.