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 skills add saajunaid/caddis-plugin --skill lldgit clone --depth 1 https://github.com/saajunaid/caddis-pluginWrote 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/skills/saajunaid/caddis-plugin/lld)<a href="https://agentmods.dev/skills/saajunaid/caddis-plugin/lld"><img src="https://agentmods.dev/badge/skills/saajunaid/caddis-plugin/lld/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/skills/saajunaid/caddis-plugin/lld"><img src="https://agentmods.dev/badge/skills/saajunaid/caddis-plugin/lld.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 | $0.00028 | $0.03475 |
| Opus 5.5 | $0.00011 | $0.01390 |
| Sonnet 5.5 | $0.00006 | $0.00695 |
| Haiku 4.5 | $0.00003 | $0.00347 |
Grade A, and why
lld 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 19d 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lower-Level Design (LLD) Authoring Skill
Overview
This skill generates Lower-Level Design (LLD) documents for enterprise application fleet systems. It documents the complete internal engineering workings: hosts, services, internal API endpoints, physical database schemas, stored procedures, ETL batches, background worker threads, data contracts, and failure recovery modes. It converts documents to Confluence Storage Format XHTML using native PlantUML (<ac:structured-macro ac:name="plantuml">) diagrams with high contrast, crisp 200 DPI vector rendering, dynamic orientation, auto-wrapped labels, and clean embedded Creole legends.
Mandatory Workflow Steps
Step 1: Deep Codebase and Schema Dissection
Analyze the target codebase and underlying database environment to dissect:
- Physical hosting, processes, service managers (NSSM, systemd), ports, and thread loops.
- All ETL scripts, batch commands, cron/scheduler configurations, source/target tables, row volumes, and idempotency logic.
- Stored procedures: signatures, parameters, join logic, analytical thresholds, and exception outputs.
- Background workers, polling loops, watermark synchronization, and caching tiers.
- UI-to-SQL query lineage: map UI screens and routes to stable query identifiers (
QRY-*) and database objects.
Step 2: Component & Interface Classification Interview (Grill-Me)
MANDATORY GATE: Before generating architecture diagrams or drafting the LLD, the agent MUST present the discovered internal components (SYS_Lxx) and internal interfaces (INT_Lxx) to the user and interview them to confirm classifications:
- Internal Component Classification:
- Which internal components are New / Impacted (
Impacted = Yes, red styling)? - Which components represent pre-existing external fleet databases or services (
Impacted = No, blue styling)?
- Which internal components are New / Impacted (
- Internal Interface Classification:
- Confirm which internal connections represent New Connectivity (
#DC2626Red) vs Existing Connectivity (#16A34AGreen).
- Confirm which internal connections represent New Connectivity (
- Present clear recommendations based on codebase findings, allowing the user to confirm or adjust classifications in a single interactive turn.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 19d ago Changed · -4 tokens per session 3ea3383d81f5
- 29d ago Changed · +104 lines · +4 tokens per session 42d3af24bda9
- 1mo ago First seen · 95 lines · 28 tokens per session scan A cf8b228899c2
lld is a skill published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed 2d ago), licensed MIT. It adds 28 tokens to every session and 3,475 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-18.
Other skills, from other repositories
goga-cookbook
Principles for applying DSL specification in cell and CODEMANIFEST design.
goga-review-plan
Verify execution plan completeness and correctness.
goga-define-experience
Define the user experience required to achieve the established product goals and solve the identified problem.
goga-define-requirements
Define the product requirements that describe what the product must do to deliver the established user experience and achieve the agreed product goals.
goga-task-by-specifying
Interactive task formulation from a raw request.
goga-discover
Interview the user relentlessly about a decision until every branch of the design tree is resolved, then record the result as a short ADR.