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/k-kolomeitsev/data-structure-protocol/dsp-refactor-safetygit clone --depth 1 https://github.com/k-kolomeitsev/data-structure-protocolWrote 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/k-kolomeitsev/data-structure-protocol/dsp-refactor-safety)<a href="https://agentmods.dev/rules/k-kolomeitsev/data-structure-protocol/dsp-refactor-safety"><img src="https://agentmods.dev/badge/rules/k-kolomeitsev/data-structure-protocol/dsp-refactor-safety.svg" alt="Measured on agentmods" 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 | $0.00006 | $0.00416 |
| Opus 5 | $0.00003 | $0.00208 |
| Sonnet 5 | $0.00001 | $0.00083 |
| Haiku 4.5 | $0.00001 | $0.00042 |
Grade A, and why
dsp-refactor-safety 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 5d 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
DSP — Refactor Safety
Before refactoring code that other modules depend on, perform impact analysis using DSP.
Step 1: Identify the Entity
dsp-cli find-by-source <file-being-refactored>
Step 2: Check Who Depends on It
# Direct dependents — who imports this entity
dsp-cli get-parents <uid>
# All importers with their reasons
dsp-cli get-recipients <uid>
Step 3: Assess Impact
- If
get-parentsreturns entities → changing this entity's interface will break them - If
get-recipientsreturns consumers → changing shared exports will affect downstream consumers - Review the
whyreason recorded for each import to understand the coupling
Step 4: Refactor Safely
After making changes:
- Renamed file →
dsp-cli move-entity <uid> <new-path> - Changed public API → update shared exports:
dsp-cli remove-shared/dsp-cli create-shared - Removed dependency →
dsp-cli remove-import <uid> <target-uid>(add--exporter <uid>if the import was registered with one) - Added dependency →
dsp-cli add-import <uid> <target-uid> "<reason>" - Updated purpose →
dsp-cli update-description <uid> --purpose "<new purpose>" - Moved to another subproject/root →
dsp-cli move-to-toc <uid> --from <TOC> --to <TOC>(+move-entityif the path changed)
Step 5: Verify
dsp-cli get-orphans # no dangling entities
dsp-cli detect-cycles # no circular dependencies
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.
- 5d ago First seen · 50 lines · 6 tokens per session scan A 8c0d31cea308
dsp-refactor-safety is a cursor rule published in the GitHub repository k-kolomeitsev/data-structure-protocol (65 stars, last pushed 25d ago), licensed Apache-2.0. It adds 6 tokens to every session and 416 once invoked, about $0.0000 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-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-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.
cursor-mcp-optimization
Cursor 3.7 MCP optimization: browser Design Mode, canvases, Figma, Cloudflare tools, MCP Apps structured content, and direct action patterns.
minimax-mcp-tools
MCP and web-tool guidance: current-doc retrieval, direct-tool preference, MCP Apps structured content, and version-aware external lookups.