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 commands/zd8899/tdad/review-commitgit clone --depth 1 https://github.com/zd8899/TDADWhat 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 | $0.01823 |
| Opus 5 | $0.00000 | $0.00911 |
| Sonnet 5 | $0.00000 | $0.00365 |
| Haiku 4.5 | $0.00000 | $0.00182 |
Grade A, and why
review-commit 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 2d 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review & Commit — TDAD VS Code Extension
You are an expert software architect reviewing and committing changes to the TDAD (Test-Driven AI Development) VS Code extension.
Follow every phase below in order. Do NOT skip phases. Report findings clearly to the user before making any changes.
CONTEXT: TDAD Architecture
What This Project Is
TDAD is a VS Code extension for workflow-based app building with multi-model AI code generation. It enforces a Plan > Spec > Test > Fix cycle where automated tests validate every line, ensuring working software.
Clean Architecture Layers
| Layer | Path | Purpose | Import Rules |
|---|---|---|---|
| Core | /src/core/ |
Business logic (ai, nodes, templates, testing, workflows, prompts) | NEVER imports from infrastructure/presentation/vscode-integration |
| Infrastructure | /src/infrastructure/ |
Technical implementations (database, parsing, storage, navigation) | MAY import from core |
| Presentation | /src/presentation/webview/ |
React UI components (.tsx, handlers, hooks, utils) | MAY import from core and infrastructure |
| VSCode Integration | /src/vscode-integration/ |
VSCode APIs (bootstrap, controllers, providers) | Coordinates all layers |
| Shared | /src/shared/ |
Cross-layer code (config, types, utils) | Imported by ALL layers |
| Styles | /src/styles/ |
All CSS files (.css) go here ONLY | N/A |
| Entry | /src/extension.ts |
Extension entry point | N/A |
Key Subsystems
- Prompt System: Template-based
.mdfiles in/src/core/prompts/with Handlebars-like syntax. Copied to.tdad/prompts/for user customization. - Autopilot: Automated BDD > Test > Run+Fix pipeline. Supports single-node and multi-feature (regression) modes.
- Golden Packet: The context packet sent to AI agents with specs, test results, traces, and rules.
- Canvas: React-based workflow editor rendered in a VSCode webview.
PHASE 1: DISCOVERY
Run in parallel:
git status
git diff --stat
git diff
git log --oneline -5
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.
- 2d ago First seen · 214 lines · 0 tokens per session scan A 37d5b9fac025
review-commit is a command published in the GitHub repository zd8899/TDAD (79 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,823 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 2026-08-30.
Other commands, from other repositories
upgrade
Upgrade the skillshare CLI binary and/or the built-in skillshare skill.
cost-tracker
Track session costs, understand token spend, and get optimization tips.
t800-onboard
Для чата с новичками. Показывает, что настроено в Cursor (global + local), и что умеет отдел T-800.
connect
Connect this workspace with another (two-way) for messaging.
session-log
Create or append a session log entry.
monitor-list
Show all metric monitors with their current status.