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/workflowgit 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 | $0.00514 | $0.00514 |
| Opus 5 | $0.00257 | $0.00257 |
| Sonnet 5 | $0.00103 | $0.00103 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
workflow 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 3d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow Rules
This file is the Cursor adapter for workflow procedures.
Detailed procedures live in skills/workflow/*.md.
Step 0
When the user's intent matches a workflow operation, first load the matching canonical file:
| Intent | Canonical procedure |
|---|---|
| Session start / current state summary | skills/workflow/session-start.md |
| Session summary / handoff | skills/workflow/session-summary.md |
| Select next work | skills/workflow/work-select.md |
| Register / add a work item | skills/workflow/work-register.md |
| Start / plan a specific task | skills/workflow/work-plan.md |
| Resume interrupted work | skills/workflow/work-resume.md |
| Close Work as Done | skills/workflow/work-close.md |
| Debug a scoped issue | skills/workflow/work-debug.md |
| Create strategy/comparison/position brief or classify a document | skills/workflow/work-brief.md |
| Run optional cross-agent review relay | skills/workflow/cross-review.md |
| Create presentation/report/review material | skills/workflow/work-doc.md |
| Repository health / cascade audit | skills/workflow/repo-health.md |
| Record a decision as DR | skills/workflow/record-decision.md |
| Merge / PR branch integration | Follow docs/GIT-WORKFLOW.md when present |
Hard Stops
- If the required
skills/workflow/{command}.mdfile is missing or unreadable, stop before editing files, changing state, committing, opening a PR, or merging. Report the missing canonical file and ask the user how to proceed. - Before any file edit, state change, commit, PR creation, or merge, enforce branch isolation, the Approval Matrix, and validation-before-commit/PR gates.
- Do not duplicate detailed checklists or cascade matrices in this adapter. Use the canonical workflow file for detailed procedure.
Entry Mechanism
Cursor has no Claude slash command file and no Codex skill directory. This rule maps natural-language intent to the canonical workflow file.
Language Policy
- This Cursor rule is English Only.
- Korean-primary workflow details belong in
skills/workflow/*.md,docs/*.md, prompts, and Claude/Codex adapters as defined bydocs/decisions/DR-007-language-policy.md.
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.
- 3d ago First seen · 47 lines · 514 tokens per session scan A 368f9a5c50aa
workflow 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 514 tokens to every session, about $0.0026 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.
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.
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-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.