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/bia-technologies/yaxunit/implement-mode-mapgit clone --depth 1 https://github.com/bia-technologies/yaxunitWhat 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 | $0.00000 | $0.02613 |
| Opus 5 | $0.00000 | $0.01307 |
| Sonnet 5 | $0.00000 | $0.00523 |
| Haiku 4.5 | $0.00000 | $0.00261 |
Grade A, and why
implement-mode-map 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 today.
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.
Copies of this mod
4 near-identical copies found in the catalogue:
- implement-mode-map — 100% identical, 0 lines differ
- implement-mode-map — 100% identical, 0 lines differ
- implement-mode-map — 100% identical, 0 lines differ
- implement-mode-map — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BUILD MODE: CODE EXECUTION PROCESS MAP
TL;DR: This visual map guides the BUILD mode process, focusing on efficient code implementation based on the planning and creative phases, with proper command execution and progress tracking.
🧭 BUILD MODE PROCESS FLOW
graph TD
Start["START BUILD MODE"] --> ReadDocs["Read Reference Documents<br>Core/command-execution.md"]
%% Initialization
ReadDocs --> CheckLevel{"Determine<br>Complexity Level<br>from tasks.md"}
%% Level 1 Implementation
CheckLevel -->|"Level 1<br>Quick Bug Fix"| L1Process["LEVEL 1 PROCESS<br>Level1/quick-bug-workflow.md"]
L1Process --> L1Review["Review Bug<br>Report"]
L1Review --> L1Examine["Examine<br>Relevant Code"]
L1Examine --> L1Fix["Implement<br>Targeted Fix"]
L1Fix --> L1Test["Test<br>Fix"]
L1Test --> L1Update["Update<br>tasks.md"]
%% Level 2 Implementation
CheckLevel -->|"Level 2<br>Simple Enhancement"| L2Process["LEVEL 2 PROCESS<br>Level2/enhancement-workflow.md"]
L2Process --> L2Review["Review Build<br>Plan"]
L2Review --> L2Examine["Examine Relevant<br>Code Areas"]
L2Examine --> L2Implement["Implement Changes<br>Sequentially"]
L2Implement --> L2Test["Test<br>Changes"]
L2Test --> L2Update["Update<br>tasks.md"]
%% Level 3-4 Implementation
CheckLevel -->|"Level 3-4<br>Feature/System"| L34Process["LEVEL 3-4 PROCESS<br>Level3/feature-workflow.md<br>Level4/system-workflow.md"]
L34Process --> L34Review["Review Plan &<br>Creative Decisions"]
L34Review --> L34Phase{"Creative Phase<br>Documents<br>Complete?"}
L34Phase -->|"No"| L34Error["ERROR:<br>Return to CREATIVE Mode"]
L34Phase -->|"Yes"| L34DirSetup["Create Directory<br>Structure"]
L34DirSetup --> L34VerifyDirs["VERIFY Directories<br>Created Successfully"]
L34VerifyDirs --> L34Implementation["Build<br>Phase"]
%% Implementation Phases
L34Implementation --> L34Phase1["Phase 1<br>Build"]
L34Phase1 --> L34VerifyFiles["VERIFY Files<br>Created Successfully"]
L34VerifyFiles --> L34Test1["Test<br>Phase 1"]
L34Test1 --> L34Document1["Document<br>Phase 1"]
L34Document1 --> L34Next1{"Next<br>Phase?"}
L34Next1 -->|"Yes"| L34Implementation
L34Next1 -->|"No"| L34Integration["Integration<br>Testing"]
L34Integration --> L34Document["Document<br>Integration Points"]
L34Document --> L34Update["Update<br>tasks.md"]
%% Command Execution
L1Fix & L2Implement & L34Phase1 --> CommandExec["COMMAND EXECUTION<br>Core/command-execution.md"]
CommandExec --> DocCommands["Document Commands<br>& Results"]
%% Completion & Transition
L1Update & L2Update & L34Update --> VerifyComplete["Verify Build<br>Complete"]
VerifyComplete --> UpdateProgress["Update progress.md<br>with Status"]
UpdateProgress --> Transition["NEXT MODE:<br>REFLECT MODE"]
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.
- today First seen · 321 lines · 0 tokens per session scan A fce8bda07239
implement-mode-map is a cursor rule published in the GitHub repository bia-technologies/yaxunit (322 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,613 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 2026-09-01.
Other cursor rules, from other repositories
cursorrules
CLAUDE.md.
telegram-bot-tests
Test conventions for Telegram Bot library.
1c-coding-standards
Стандарты кода BSL: именование, запросы, коллекции.
1c-skd-two-pass-preprocessing
Двухпроходный СКД: предобработка детальных записей до свертки.
model-selection
Стратегия выбора моделей: Opus/Sonnet/Haiku по типу задачи.
zpa-dependency-chain
ZPA application onboarding requires resources to be created in a specific dependency order. Skipping dependencies causes cryptic 400 errors.