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 vikram-vn/cpq-bml --skill bml-pitfallsgit clone --depth 1 https://github.com/vikram-vn/cpq-bmlWrote 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/vikram-vn/cpq-bml/bml-pitfalls)<a href="https://agentmods.dev/skills/vikram-vn/cpq-bml/bml-pitfalls"><img src="https://agentmods.dev/badge/skills/vikram-vn/cpq-bml/bml-pitfalls/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/vikram-vn/cpq-bml/bml-pitfalls"><img src="https://agentmods.dev/badge/skills/vikram-vn/cpq-bml/bml-pitfalls.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 | $0.00024 | $0.00558 |
| Opus 5 | $0.00012 | $0.00279 |
| Sonnet 5 | $0.00005 | $0.00112 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade A, and why
bml-pitfalls 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 9d 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
BML Pitfalls & Anti-Patterns
1. Syntax & Keywords
- Do NOT use
var,let, orconst: BML has no variable declaration keywords. Direct assignment only:myVar = "value";. - Do NOT use C-style logical operators
&&,||, or!: Strictly use BML keywordsAND,OR, andNOT(condition). - Use
==and<>, NOT===and!=: In BML,<>is the canonical not-equal operator. - Always terminate statements with
;: Every BML statement must end with a semicolon. - Single statement per line: Avoid placing multiple statements on the same line.
2. Nesting & Performance
- Loop Nesting Limit (Max 3): Loop nesting depth must not exceed 3 (warning at depth 4+). Flatten loops using Maps/Dictionaries or helper functions.
- Block & Condition Nesting Limit (Max 5): Condition/block nesting depth must not exceed 5 (warning at depth 6+).
- Avoid Repeated BMQL inside loops: Fetch bulk data into a RecordSet or Dictionary outside loops to avoid N+1 query overhead.
3. Data Types & Comparisons
- NULL vs Blank String:
- NULL for integers/numbers evaluates to
0. - Blank string evaluates to
"". - NULL and blank strings are treated as separate values in CPQ. Confirm comparison logic accounts for this difference.
- NULL for integers/numbers evaluates to
- Array Size Limits:
- Default BML row size limit is 5000; default column size limit is 50.
- Dictionary Value Constraints:
- Legacy typed dictionaries (e.g.
dict("string")) cannot hold nested dictionaries. Usedict("anytype")or JSON objects (json(),jsonarray()) for nested structures.
- Legacy typed dictionaries (e.g.
4. Security & BMQL
- SQL Injection Prevention: Never concatenate raw input parameters directly into BMQL query strings. Always use dynamic BMQL
$variablesubstitution. - BMQL Cap Limit: Statements using
UPDATE,MODIFY,DISTINCT, orORDER BYprocess or return a maximum of 1,000 records.
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.
- 9d ago First seen · 37 lines · 24 tokens per session scan A eed04ee8934f
bml-pitfalls is a skill published in the GitHub repository vikram-vn/cpq-bml (0 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 558 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
otter-rules-engine
This skill should be used when the user asks to "add a rule", "create a ruleset", "add a fact", "create a custom operator", "add a rules-engine action", "make behavior conditional at runtime", or when authoring or debugging anything in an Otter @o3r/rules-engine workspace. Guides the fact/operator/action/ruleset…
playwright-e2e-testing
This skill should be used when the user asks to "create an E2E test", "write a Playwright scenario", "add a Playwright test", "generate e2e tests", "create actions and checks", "write playwright checks", "add scenario for feature", or when modifying, reviewing, or debugging Playwright E2E test files in the workspace.
validate
MUST be used whenever a user or agent asks to find problems, check for issues, or validate changes in a Spring Boot project. Uses the spring-tools MCP server to check for validation problems in the project's source files.
citevahti-support
Use when handling a CiteVahti user report — triaging a bug report or pilot-user email, updating the known-issues register, drafting a support reply, or deciding whether a report needs immediate escalation. Data-loss and false-verified reports escalate immediately. Maintainer-facing; mandatory from the first paying…
gh-fix-ci
Debug failing GitHub Actions CI checks on the current branch's PR using the gh CLI — inspect logs, summarize root cause, and propose a focused fix plan before implementing.
grafema-codebase-analysis
Analyze codebases using a graph database instead of reading source files. Use when understanding code architecture, finding functions or call patterns, tracing data flow, checking dependencies, or answering "where is X used?" questions. Grafema builds a queryable code graph from static analysis — prefer querying the…