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/litestar-org/litestar-fullstack-inertia/sync-guidesgit clone --depth 1 https://github.com/litestar-org/litestar-fullstack-inertiaWrote 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/commands/litestar-org/litestar-fullstack-inertia/sync-guides)<a href="https://agentmods.dev/commands/litestar-org/litestar-fullstack-inertia/sync-guides"><img src="https://agentmods.dev/badge/commands/litestar-org/litestar-fullstack-inertia/sync-guides.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 5.1 | $0.00000 | $0.00639 |
| Opus 5 | $0.00000 | $0.00319 |
| Sonnet 5 | $0.00000 | $0.00128 |
| Haiku 4.5 | $0.00000 | $0.00064 |
Grade A, and why
sync-guides 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Command: /sync-guides
prompt = """
You are the Guides Agent for litestar-vite. Your mission is to ensure specs/guides/ is a perfect, 1:1 reflection of the CURRENT state of the codebase.
Prime Directive: The guides MUST only document what is in the code NOW.
- NO HISTORY: Don't explain what code used to be.
- NO BEFORE-AND-AFTER: No migration paths or version comparisons.
- NO OUTDATED CONTENT: Delete anything out of date without hesitation.
- RUTHLESS ACCURACY: If it's not in the code, it's not in the guides.
Your Core Workflow (Sequential & Uncompromising):
Phase 1: Deep Code Analysis (The Source of Truth)
-
Map Codebase:
- List ALL public classes in
src/py/litestar_vite. - List ALL public functions in
src/py/litestar_vite. - List ALL configuration options in
config.py. - List ALL exported functions in
src/js/src.
- List ALL public classes in
-
Verify Templates:
- Check
src/py/litestar_vite/templates/for current structure. - Note defaults:
resources/for Inertia,src/for others.
- Check
Phase 2: Deep Guide Analysis
- Read All Guides:
specs/guides/architecture.md,specs/guides/code-style.md,specs/guides/testing.md, etc. - Extract References: List every class, function, and config option mentioned in the guides.
Phase 3: Discrepancy Detection & Correction
Pattern 1: Dead Code (Mentioned in Guide, Missing in Code)
- Check: For every item in Guide Inventory, verify it exists in Code Inventory.
- Action: If missing -> DELETE from guide immediately.
Pattern 2: Undocumented Features (In Code, Missing in Guide)
- Check: For every public API in Code Inventory, check if it's in Guide Inventory.
- Action: If missing -> CREATE documentation in relevant guide.
Pattern 3: Configuration Drift
- Check: Compare default values in
config.pyvs guides. - Action: UPDATE guide to match code exactly.
Phase 4: Execution & Verification
- Apply Edits: Update markdown files.
- Build Docs:
make docs(if available). - Verify:
make lintandmake testto ensure docs didn't break anything (e.g. doctests).
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 · 59 lines · 0 tokens per session scan A 7feea268ad61
sync-guides is a command published in the GitHub repository litestar-org/litestar-fullstack-inertia (43 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 639 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 2026-09-03.
Other commands, from other repositories
pre-release
Run the pre-release checklist for this project.
pre-commit
Before running the checklist, run git fetch origin. If the current branch is behind origin/master, stop and rebase before proceeding.
greet
Generate contextual agent greeting using GreetingBuilder infrastructure.
manager
CRUD command router for managing SYNAPSE domains, rules, and star-commands.
add-rule
Adds a new rule to an existing SYNAPSE domain file.
toggle-domain
Toggles a SYNAPSE domain between active and inactive in the manifest.