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/alpyenigun/eliniscan/fixgit clone --depth 1 https://github.com/AlpYenigun/eliniscanWhat 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 | $0.00024 | $0.01892 |
| Opus 5 | $0.00012 | $0.00946 |
| Sonnet 5 | $0.00005 | $0.00378 |
| Haiku 4.5 | $0.00002 | $0.00189 |
Grade A, and why
eliniscan:fix 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRITICAL: Do NOT fix files yourself. Generate a bash script and run it in background with nohup.
- Verify ELINISCAN-FINDINGS.md exists. If not, tell user to run
/eliniscan:scanfirst. - Count findings and files with issues.
- Ask user:
eliniscan Fix
Found {X} issues in {Y} files.
Which model for fixing?
1. Opus — Most accurate fixes (slower)
2. Sonnet — Fast and reliable (recommended)
Severity filter?
1. All — Fix everything
2. High — Only CRITICAL and HIGH
3. Critical — Only CRITICAL
STEP 2: Generate extract-findings.py helper
Write this Python helper to /tmp/eliniscan_extract.py:
#!/usr/bin/env python3
import sys, re
def extract(findings_path, target_file):
with open(findings_path, 'r') as f:
content = f.read()
blocks = re.split(r'^### ', content, flags=re.MULTILINE)
for block in blocks[1:]:
lines = block.strip().split('\n')
filepath = lines[0].strip()
if filepath != target_file:
continue
body = '\n'.join(lines[1:]).strip()
if body and body != 'CLEAN':
print(body)
return
if __name__ == '__main__':
extract(sys.argv[1], sys.argv[2])
STEP 3: Generate and launch fix script
Write to /tmp/eliniscan_fix.sh:
#!/bin/bash
set -uo pipefail
PROJECT_DIR="$(pwd)"
FINDINGS="$PROJECT_DIR/ELINISCAN-FINDINGS.md"
FIX_TRACKING="$PROJECT_DIR/FIX-TRACKING.md"
EXTRACT_PY="/tmp/eliniscan_extract.py"
PROGRESS="/tmp/eliniscan_fix_progress.txt"
LOG="/tmp/eliniscan_fix.log"
TEMP_FIX="/tmp/eliniscan_fix_result.txt"
# Get files with findings
FILE_LIST="/tmp/eliniscan_fix_files.txt"
grep '^### ' "$FINDINGS" | sed 's/### //' | sort -u > "$FILE_LIST"
TOTAL=$(wc -l < "$FILE_LIST" | tr -d ' ')
echo "eliniscan fix started: $TOTAL files" > "$LOG"
# Init tracking
cat > "$FIX_TRACKING" << 'HEADER'
# eliniscan Fix Tracking
| # | File | Status | Details | Date |
|---|------|--------|---------|------|
HEADER
FIXED=0
SKIPPED=0
CURRENT=0
while IFS= read -r REL_PATH; do
CURRENT=$((CURRENT + 1))
FILEPATH="$PROJECT_DIR/$REL_PATH"
if [[ ! -f "$FILEPATH" ]]; then
echo "[$CURRENT/$TOTAL] SKIP (missing): $REL_PATH" >> "$LOG"
SKIPPED=$((SKIPPED + 1))
echo "$CURRENT/$TOTAL" > "$PROGRESS"
continue
fi
FILE_FINDINGS=$(python3 "$EXTRACT_PY" "$FINDINGS" "$REL_PATH" 2>/dev/null)
if [[ -z "$FILE_FINDINGS" ]]; then
echo "[$CURRENT/$TOTAL] SKIP (no findings): $REL_PATH" >> "$LOG"
SKIPPED=$((SKIPPED + 1))
echo "$CURRENT/$TOTAL" > "$PROGRESS"
continue
fi
LINE_COUNT=$(wc -l < "$FILEPATH" | tr -d ' ')
echo "[$CURRENT/$TOTAL] FIX: $REL_PATH ($LINE_COUNT lines)" >> "$LOG"
PROMPT="You are a code fixer. Fix ALL issues listed below. Return the COMPLETE fixed file.
RULES:
1. ONLY fix the reported issues — change nothing else
2. Do NOT change import/export signatures (breaking change)
3. Do NOT add new dependencies
4. Do NOT add module-level throw statements — they crash Next.js build
5. Do NOT wrap entire files in try/catch
6. For missing env vars: use fallback values or runtime checks, NOT build-time throws
7. Return ONLY code — no explanations, no markdown fences, no comments about what you fixed
8. If a fix would break existing behavior, SKIP that fix
9. Return the ENTIRE file
ISSUES:
$FILE_FINDINGS
FILE ($REL_PATH):
$(cat "$FILEPATH")"
if echo "$PROMPT" | claude --print --model {MODEL} -p - > "$TEMP_FIX" 2>/dev/null; then
FIX_LINES=$(wc -l < "$TEMP_FIX" | tr -d ' ')
if [[ "$FIX_LINES" -lt 3 ]]; then
echo " SKIP (empty result)" >> "$LOG"
SKIPPED=$((SKIPPED + 1))
echo "| $CURRENT | $REL_PATH | SKIPPED | empty result | $(date +%Y-%m-%d) |" >> "$FIX_TRACKING"
echo "$CURRENT/$TOTAL" > "$PROGRESS"
continue
fi
# Strip markdown fences if present
if head -1 "$TEMP_FIX" | grep -q '^\`\`\`'; then
sed -i '' '1d' "$TEMP_FIX"
if tail -1 "$TEMP_FIX" | grep -q '^\`\`\`'; then
sed -i '' '$d' "$TEMP_FIX"
fi
fi
# Validate: first line should look like code
FIRST_LINE=$(head -1 "$TEMP_FIX")
if echo "$FIRST_LINE" | grep -qiE '^(import |"use |export |//|/\*|const |let |var |function |class |interface |type |enum |\{|$)'; then
cp "$TEMP_FIX" "$FILEPATH"
FIXED=$((FIXED + 1))
echo " FIXED" >> "$LOG"
echo "| $CURRENT | $REL_PATH | FIXED | - | $(date +%Y-%m-%d) |" >> "$FIX_TRACKING"
else
echo " SKIP (not code)" >> "$LOG"
SKIPPED=$((SKIPPED + 1))
echo "| $CURRENT | $REL_PATH | SKIPPED | output not code | $(date +%Y-%m-%d) |" >> "$FIX_TRACKING"
fi
else
echo " SKIP (claude error)" >> "$LOG"
SKIPPED=$((SKIPPED + 1))
echo "| $CURRENT | $REL_PATH | ERROR | claude failed | $(date +%Y-%m-%d) |" >> "$FIX_TRACKING"
fi
echo "$CURRENT/$TOTAL" > "$PROGRESS"
sleep 2
done < "$FILE_LIST"
echo "" >> "$LOG"
echo "FIX COMPLETE: $FIXED fixed, $SKIPPED skipped" >> "$LOG"
echo "DONE" > "$PROGRESS"
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 · 226 lines · 24 tokens per session scan A e5ecb1258fd7
eliniscan:fix is a command published in the GitHub repository AlpYenigun/eliniscan (3 stars, last pushed 6d ago), licensed MIT. It adds 24 tokens to every session and 1,892 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.