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 EliBarak12/Elliot --skill lint-connectorgit clone --depth 1 https://github.com/EliBarak12/ElliotWrote 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/elibarak12/elliot/lint-connector)<a href="https://agentmods.dev/skills/elibarak12/elliot/lint-connector"><img src="https://agentmods.dev/badge/skills/elibarak12/elliot/lint-connector/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/elibarak12/elliot/lint-connector"><img src="https://agentmods.dev/badge/skills/elibarak12/elliot/lint-connector.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 | $0.00034 | $0.01222 |
| Opus 5 | $0.00017 | $0.00611 |
| Sonnet 5 | $0.00007 | $0.00244 |
| Haiku 4.5 | $0.00003 | $0.00122 |
Grade A, and why
lint-connector 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 10d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lint Connector Workflow
Connector files
!ls connectors/*.connector.json 2>/dev/null || echo "(no connectors found)"
Steps
1. Run lint
elliot_lint_connector lints the connector currently built in the session and
takes no arguments. If nothing has been built yet, call elliot_build_connector
first (use elliot_list_tools to see what tools are registered). To lint an
existing connector file, load it into the session and build it before linting.
2. Read every issue
For each issue reported:
| Severity | Action |
|---|---|
error |
Must fix — connector won't pass validation |
warning |
Should fix — hurts agent accuracy |
info |
Optional — quality improvement |
3. Fix the issues by code
The linter emits stable UPPER_SNAKE codes (the exact strings you'll see in the output). The common ones and how to fix them:
| Code | Severity | Fix |
|---|---|---|
DESCRIPTION_TOO_SHORT |
error | Write ≥15 chars: "<Verb> <object>. Use when <context>. Returns <fields>. <constraint>." |
DESCRIPTION_MISSING_VERB |
warn | Start the description with a verb — "Return…", "List…", "Create…", "Count…". |
UNBOUNDED_SELECT |
error | A SELECT * with no WHERE or LIMIT. Add LIMIT :limit or a filter parameter. |
SELECT_STAR_NO_LIMIT |
warn | Replace SELECT * with an explicit column list, or add a LIMIT. |
MISSING_PAGINATION |
warn | List-style READ tool with no LIMIT/cursor — add LIMIT :limit or a limit/offset/cursor parameter. |
PARAMETER_NAME_GENERIC / _TOO_SHORT |
warn | Rename to something specific: customer_id, order_status. |
PARAMETER_MISSING_DESCRIPTION |
warn | Add a description so agents know what to pass. |
PARAMETER_SHOULD_BE_ENUM |
warn | Declare the fixed value set as an enum. |
FILTER_SEMANTICS_UNCLEAR |
warn | In the parameter's own description, state exact / contains / prefix / case-insensitive matching. |
WRITE_TOOL_DESCRIPTION |
info | Add the mutation verb ("Creates…", "Deletes…") to a WRITE/ACTION tool. |
SENSITIVE_FIELD_EXPOSED |
error | A field the product intent marked never-expose appears in this tool's SQL/output or its forwarded rest_query_params / api_mapping body/query params. Drop or redact it. |
SECRET_IN_URL |
error | A secret is embedded in source.url. Move it to auth.secret_key as {{ env:VAR }}. |
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.
- 10d ago First seen · 88 lines · 34 tokens per session scan A 7ec484df091f
lint-connector is a skill published in the GitHub repository EliBarak12/Elliot (11 stars, last pushed 10d ago), licensed MIT. It adds 34 tokens to every session and 1,222 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
langsmith-tracing
LangSmith tracing and debugging setup for LLM applications. Configure observability, capture traces, and enable debugging for LangChain/LangGraph agents.
behavior-contract
Bug condition/postcondition formalization as testable Behavior Contracts. Defines invariants that must be preserved across fixes.
quality-hooks
Language-specific auto-lint/format/typecheck pipeline. Supports Python (ruff+pyright), TypeScript (prettier+eslint+tsc), Go (gofmt+golangci-lint). Auto-fix and convergence loops.
systematic-debugging
Structured debugging methodology using hypothesis-driven investigation, log analysis, and bisection to isolate and resolve defects.
debugging-patterns
Root cause analysis frameworks including log-first investigation, git bisect correlation, and pattern-based diagnosis with confidence scoring.
hotfix-triage
Urgent issue classification, root cause analysis, and fast-path routing for production hotfixes.