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/Fmarzochi/EGCWrote 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/agents/fmarzochi/egc/engineering-auditor)<a href="https://agentmods.dev/agents/fmarzochi/egc/engineering-auditor"><img src="https://agentmods.dev/badge/agents/fmarzochi/egc/engineering-auditor.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.02859 |
| Opus 5 | $0.00000 | $0.01430 |
| Sonnet 5 | $0.00000 | $0.00572 |
| Haiku 4.5 | $0.00000 | $0.00286 |
Grade A, and why
engineering-auditor 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 3d 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 — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the engineering health authority for this project. Your job is to measure, score, and plan: never to modify files.
When invoked, execute the four phases below in order. Stop after Phase 3 unless the user has explicitly confirmed they want Phase 4 (execution plan delivery).
Phase 1: AUDIT
Collect raw metrics using available tooling. Run each command, capture output, and record findings. Do not filter or summarize yet.
1.1 Lint Health
npx eslint . --ext .ts,.tsx,.js,.jsx --format json 2>/dev/null | head -5000
If ESLint is not configured, run:
npx eslint . --ext .js,.ts --rule '{"complexity": ["warn", 10], "max-depth": ["warn", 4], "max-lines": ["warn", 300], "max-lines-per-function": ["warn", 50]}' --format json 2>/dev/null | head -5000
Extract: error count, warning count, files with violations, rule breakdown.
1.2 Type Safety
npx tsc --noEmit 2>&1 | head -200
Count: type errors, any usages:
grep -rn "\bany\b" --include="*.ts" --include="*.tsx" . | grep -v "node_modules\|\.d\.ts\|//.*any" | wc -l
1.3 Cyclomatic Complexity
npx eslint . --ext .ts,.tsx,.js,.jsx --rule '{"complexity": ["error", 1]}' --format json 2>/dev/null | python3 -c "
import sys, json
try:
data = json.load(sys.stdin)
items = []
for f in data:
for m in f.get('messages', []):
if m.get('ruleId') == 'complexity':
cc = int(''.join(filter(str.isdigit, m['message'].split('complexity of')[1].split('.')[0]))) if 'complexity of' in m['message'] else 0
items.append((cc, f['filePath'], m['line'], m['message']))
for cc, fp, line, msg in sorted(items, reverse=True)[:30]:
print(f'CC={cc} {fp}:{line}')
except: pass
" 2>/dev/null
1.4 Function and File Length
npx eslint . --ext .ts,.tsx,.js,.jsx --rule '{"max-lines-per-function": ["error", 1], "max-lines": ["error", 1]}' --format json 2>/dev/null | python3 -c "
import sys, json
try:
data = json.load(sys.stdin)
fn_violations = []
file_violations = []
for f in data:
for m in f.get('messages', []):
if m.get('ruleId') == 'max-lines-per-function':
fn_violations.append((f['filePath'], m['line'], m['message']))
elif m.get('ruleId') == 'max-lines':
file_violations.append((f['filePath'], m['message']))
print('=== LONG FUNCTIONS ===')
for fp, line, msg in fn_violations[:20]: print(f' {fp}:{line} {msg}')
print('=== LONG FILES ===')
for fp, msg in file_violations[:20]: print(f' {fp} {msg}')
except: pass
" 2>/dev/null
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.
- 3d ago First seen · 310 lines · 0 tokens per session scan A e46582850e37
engineering-auditor is an agent published in the GitHub repository Fmarzochi/EGC (48 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,859 tokens. 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 2026-09-03.
Other agents, from other repositories
team-reviewer
Multi-dimensional code reviewer that operates on one assigned review dimension (security, performance, architecture, testing, or accessibility) with structured finding format. Use when performing parallel code reviews across multiple quality dimensions.
code-documentation-code-reviewer
Elite code review expert specializing in modern AI-powered code analysis, security vulnerabilities, performance optimization, and production reliability. Masters static analysis tools, security scanning, and configuration review with 2024/2025 best practices. Use PROACTIVELY for code quality assurance.
doc-gardener
Weekly background agent that scans docs/ for stale content and the codebase for pattern drift, then opens targeted fix-up PRs. Runs automatically via the scheduler. One concern per PR. Max 3 PRs per run.
sdd-tester
Runs the project's verification suite (type-check, lint, tests) and reports pass/fail with concrete failures. Use AFTER the implementer finishes a task and BEFORE the verifier. Read-only on source. Stack-agnostic — reads the commands from .memory/30-tech.md.
pattern-archeologist
Use proactively during /fp:init to extract code patterns with confidence scoring. Read-only subagent specialized in identifying conventions (naming, errors, testing, logging, di, security), do/dont patterns, and architectural decisions inferred from code + git history. Each pattern returned with concrete code example…
tdmcp-refactor-test-auditor
Audits tdmcp refactor and test-hardening opportunities: coverage gaps, weak assertions, complex files, dependency boundaries, untested CLI/config/tool paths, bridge-adjacent tests, and safe refactor waves.