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.
git clone --depth 1 https://github.com/hlalljie/agent-workflow-presetsWrote 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.
[](https://agentmods.dev/rules/hlalljie/agent-workflow-presets/workflow-mode)<a href="https://agentmods.dev/rules/hlalljie/agent-workflow-presets/workflow-mode"><img src="https://agentmods.dev/badge/rules/hlalljie/agent-workflow-presets/workflow-mode/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/hlalljie/agent-workflow-presets/workflow-mode"><img src="https://agentmods.dev/badge/rules/hlalljie/agent-workflow-presets/workflow-mode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00365 | $0.00365 |
| Opus 5.5 | $0.00146 | $0.00146 |
| Sonnet 5.5 | $0.00073 | $0.00073 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
workflow-mode 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 9d 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.
What it actually says
Modes
Modes: careful, pair, afk. No mode = default. Details live in .cursor/skills/run-task-loop/modes/<mode>.md.
Switching
- Only the user switches modes. Never switch yourself or suggest a switch.
- A message switches mode only when it names the mode with the word "mode" or the skill:
careful mode,mode: pair,/run-task-loop afk.default modeormode: defaultreturns to default. - A bare mode word ("afk", "be careful") is not a switch.
- On a switch, read the mode file now, then follow it.
- The mode applies to this chat only. Do not store it in files.
Staying in the mode
- Start every reply with
[mode: <name>]. Omit the tag in default. - A mode named in your earlier replies or in the conversation summary stays active until the user changes it.
- Re-read the mode file at the start of each new task or phase, and whenever the earlier conversation has been summarized.
Subagents
- If you are a subagent, ignore this rule: no tag, no mode file. Follow only the prompt you were given.
- When you spawn a subagent, follow the "Subagents" section of the active mode file. In default, add nothing.
- Mode text for a subagent only limits risk or questions. It never changes the subagent's task (for example, never tell a subagent that is writing tests not to write tests).
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.
- 9d ago First seen · 29 lines · 365 tokens per session scan A eceba4636f02
workflow-mode is a cursor rule published in the GitHub repository hlalljie/agent-workflow-presets (2 stars, last pushed 6d ago), licensed MIT. It adds 365 tokens to every session, about $0.0015 per session on Opus 5.5. 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 2026-10-07.
Other cursor rules, from other repositories
incremental-verify
Verify each behavior before building the next. One test, one implementation, one commit. No bulk-writing tests for behavior that does not yet exist.
context-discipline
Manage AI context window efficiently - read before write, no re-reads, tool-call budgets, one-pass discipline.
x402-coding
@dexterai/x402 SDK conventions and hosted-only OpenDexter tool usage.
pn-rust-backend
Rust backend style, env, and error handling. Use for API and server code (Actix-web, Axum).
pn-visual-indicator
Tag every pnCore-touched assistant response with a context tag plus 🔺 (red triangle emoji) so the response is visible at a glance in Cursor's chat UI.
pn-tool-risk-policy
MCP tool risk tiers, HITL gates, and when to use approvalcheckpoint and gatelogappend. Use for safety reviews and workflow audits.