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.
git clone --depth 1 https://github.com/AlpYenigun/eliniscanWrote 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/alpyenigun/eliniscan/help)<a href="https://agentmods.dev/commands/alpyenigun/eliniscan/help"><img src="https://agentmods.dev/badge/commands/alpyenigun/eliniscan/help/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/commands/alpyenigun/eliniscan/help"><img src="https://agentmods.dev/badge/commands/alpyenigun/eliniscan/help.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 | $0.00015 | $0.00657 |
| Opus 5.5 | $0.00006 | $0.00263 |
| Sonnet 5.5 | $0.00003 | $0.00131 |
| Haiku 4.5 | $0.00002 | $0.00066 |
Grade A, and why
eliniscan:help 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 1mo 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
═══════════════════════════════════════════════════
eliniscan — AI Full Codebase Scanner
https://github.com/alpyenigun/eliniscan
═══════════════════════════════════════════════════
CORE COMMANDS
/eliniscan:scan Full codebase scan (file by file, separate sessions)
/eliniscan:fix Auto-fix all found issues (batch, verify, build)
/eliniscan:report Show scan/fix summary with charts
/eliniscan:status Show current progress (scan/fix running?)
MANAGEMENT
/eliniscan:resume Resume interrupted scan or fix
/eliniscan:clean Remove all generated files and reset state
/eliniscan:settings View and modify configuration
/eliniscan:update Check for updates and install latest version
/eliniscan:help This help message
SCAN OPTIONS
--depth Full Scan every line (default)
--depth Quick Scan only critical patterns
--model Opus Most thorough (slower)
--model Sonnet Balanced (default, recommended)
--model Haiku Fastest (may miss subtle issues)
--severity All Report everything (default)
--severity High Only CRITICAL and HIGH
FIX OPTIONS
--severity Critical Fix only CRITICAL issues
--severity High Fix CRITICAL + HIGH
--severity All Fix everything (default)
--model Opus Most accurate fixes
--model Sonnet Fast and reliable (default)
WORKFLOW
1. /eliniscan:scan Scan entire codebase
2. /eliniscan:report Review findings
3. /eliniscan:fix Auto-fix issues
4. /eliniscan:scan Re-scan to verify
If interrupted at any step: /eliniscan:resume
FILES GENERATED
ELINISCAN-FINDINGS.md All issues with IDs (#001, #002...)
ELINISCAN-TRACKING.md File-by-file scan status
FIX-TRACKING.md Fix results per file
ARCHITECTURE
- CLI tool: ~/.claude/eliniscan/bin/eliniscan-tools.cjs
- Commands: ~/.claude/commands/eliniscan/
- Workflows: ~/.claude/eliniscan/workflows/
- Agents: ~/.claude/agents/eliniscan-*.md
- References: ~/.claude/eliniscan/references/
- Config: ~/.claude/eliniscan/config.json
- State: ~/.claude/eliniscan/state.json
GitHub: https://github.com/alpyenigun/eliniscan
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.
- 1mo ago First seen · 79 lines · 15 tokens per session scan A fe54129c5acc
eliniscan:help is a command published in the GitHub repository AlpYenigun/eliniscan (2 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 657 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 2026-08-31.
Other commands, from other repositories
qa-changes
This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…
auditar-cascading
Invoca cascading-failures-auditor — audita serviço para 5 triggers de cascade (sem timeout, retry sem jitter, sem circuit breaker, sem deadline, queue unbounded) e gera CASCADING-AUDIT.md.
react-native
Command "react-native" from getsentry/toolkit, covering xcode build step (react-native xcode) and important notes.
http-service
Build, review or debug a Bun HTTP service. Loads the http-service skill, then works the task through its workflow.
doctor
Diagnosticar y reparar problemas del framework Don Cheli, git y entorno. Usa cuando el usuario dice "doctor", "problemas del framework", "don cheli no funciona", "repair Don Cheli", "debug setup", "setup broken", "framework broken", "reparar entorno". Detecta y repara issues de configuración, git y dependencias…
doctor
Badi configuration validation. Checks all Badi components and produces a diagnostic report.