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/code-documentation)<a href="https://agentmods.dev/rules/hlalljie/agent-workflow-presets/code-documentation"><img src="https://agentmods.dev/badge/rules/hlalljie/agent-workflow-presets/code-documentation/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/code-documentation"><img src="https://agentmods.dev/badge/rules/hlalljie/agent-workflow-presets/code-documentation.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 | $0.00000 | $0.00327 |
| Opus 5.5 | $0.00000 | $0.00131 |
| Sonnet 5.5 | $0.00000 | $0.00065 |
| Haiku 4.5 | $0.00000 | $0.00033 |
Grade A, and why
code-documentation 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 6d 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
Document why, not what. Only add a comment if it conveys information the code itself cannot. Never narrate what the code obviously does.
Do document: purpose, constraints, trade-offs, non-obvious decisions, known debt (see TODOs below).
Do not document: obvious logic, simple wrappers, self-evident one-liners.
Module/file-level comments: explain what the module owns and any non-obvious limitations.
Comment kinds
/** */doc comment — the contract of an exported symbol, only when its name and types do not already say it: units, edge cases, side effects, failure modes. Write TSDoc style: no types in tags,@param name - descriptionwith the hyphen, and only tags that add information (@throws,@deprecatedplus what to use instead,@example).//comment — why the implementation is the way it is.
TODOs
TODO(#123): reason, pointing at the GitHub issue that tracks it. With no issue, write TODO: reason and no link. Never point at a plan or task file, because plans move (see workflow.mdc).
Do not write
- Comments that narrate the change ("now uses X", "added for Y")
- Banner or divider comments
- Comments that restate a name or type
- Edits to comments unrelated to the change
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.
- 6d ago Changed · +14 lines 5c288c54d116
- 1mo ago First seen · 16 lines · 0 tokens per session scan A d5bc02f219a0
code-documentation is a cursor rule published in the GitHub repository hlalljie/agent-workflow-presets (2 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 327 tokens. 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.
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.