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 agentmods add rules/kyungseo/ai-workflow-harness/git-commitgit clone --depth 1 https://github.com/kyungseo/ai-workflow-harnessWhat 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 | $0.00018 | $0.00644 |
| Opus 5 | $0.00009 | $0.00322 |
| Sonnet 5 | $0.00004 | $0.00129 |
| Haiku 4.5 | $0.00002 | $0.00064 |
Grade A, and why
git-commit 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.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Commit Rules
Pre-Commit Process
If the current directory is not a git repository (bootstrap initial state), report the steps below as Not Applicable and proceed with document/file validation only.
Before committing, always run in this order:
git status— confirm full working tree state (unstaged + untracked)git add <files>— stage intended filesgit status— verify nothing is missed before committinggit diff --cached— review staged content
NEVER use git diff --cached alone as the only pre-commit check.
It does not show unstaged modifications or untracked files.
Commit Approval
MUST:
- Commit only after validation is complete or the remaining risk is explicitly accepted.
- Before committing, follow the Approval Matrix: report validation result, diff summary, and proposed commit message, then wait for explicit user approval.
- Before committing or opening a PR, report STATUS Finalization: whether
docs/STATUS.mdupdate is needed, why, and the required Approval Matrix proposal if needed. - Before committing or opening a PR, report Tracking Finalization: whether backlog/Work/DR tracker updates are needed, why, and which tracker files changed if any.
- If
docs/STATUS.mdneeds to change before commit, provide the Approval Matrix state-change proposal and wait for explicit user approval before editing it. Phase/focus/recent decision changes still require a fullSTATUS Update Proposal. - If not committing after a completed task, record the reason and remaining risk in the session summary.
Commit Message
MUST use Conventional Commits with Bilingual Rules (per docs/decisions/DR-007-language-policy.md):
Type prefix — always in English: feat, fix, docs, chore, refactor, test, style, ci, config, perf, build, revert
Subject line — Korean primary; English for technical terms and identifiers.
- Use Korean verbs and sentence endings.
- Keep English for proper nouns, tool names, file paths, IDs (e.g.,
DR-007,STATUS.md). - Example:
docs: [Korean subject using DR-007 and Bilingual Rules identifiers]
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 · 68 lines · 18 tokens per session scan A 72ed8a9cbb3e
git-commit 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 18 tokens to every session and 644 once invoked, about $0.0001 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.
Other cursor rules, from other repositories
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.
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.
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.
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.
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.
cursor-mcp-optimization
Cursor 3.7 MCP optimization: browser Design Mode, canvases, Figma, Cloudflare tools, MCP Apps structured content, and direct action patterns.