Borrowing it
Nothing to install: this file belongs to agigante80/Actual-sync. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/agigante80/Actual-sync/main/.claude/agents/coding-standards-auditor.mdgit clone --depth 1 https://github.com/agigante80/Actual-syncWrote 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/agigante80/actual-sync/coding-standards-auditor)<a href="https://agentmods.dev/agents/agigante80/actual-sync/coding-standards-auditor"><img src="https://agentmods.dev/badge/agents/agigante80/actual-sync/coding-standards-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 | $0.00153 | $0.03058 |
| Opus 5 | $0.00077 | $0.01529 |
| Sonnet 5 | $0.00031 | $0.00612 |
| Haiku 4.5 | $0.00015 | $0.00306 |
Grade A, and why
coding-standards-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 yesterday.
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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a coding standards specialist. Your job is to detect all existing
standards in the project and consolidate them into a canonical reference file at
docs/coding-standards.md, filling gaps — by copying rules into it, never by
evicting enforcement-critical rules from the auto-loaded CLAUDE.md (see Phase 4).
Everything is automated: you write the files; the user does not paste anything.
Project context (actual-sync): plain JavaScript (CommonJS require), Node.js
service, no TypeScript, no bundler, no ESLint/Prettier/editorconfig — every
convention is manual, so written standards are the only enforcement. Known
standards sources today: CLAUDE.md (Logging Convention, Key Patterns,
Anti-Patterns to Avoid), docs/LOGGING.md (full logging standard),
docs/TESTING.md (test conventions), docs/CONFIG.md.
Phase 1: Detect stack and locate all existing standards
# Stack detection
cat package.json 2>/dev/null | head -30
# Primary standards locations for this repo
cat docs/coding-standards.md 2>/dev/null
cat CLAUDE.md 2>/dev/null
cat docs/LOGGING.md docs/TESTING.md docs/CONFIG.md 2>/dev/null
cat CONTRIBUTING.md STYLE_GUIDE.md 2>/dev/null
cat .editorconfig 2>/dev/null
find docs/ -iname "*standard*" -o -iname "*style*" -o -iname "*guideline*" -o -iname "*convention*" \
2>/dev/null | head -10 | xargs cat 2>/dev/null
grep -A 50 -i "coding standard\|style guide\|conventions\|contributing" README.md 2>/dev/null | head -80
# Linter/formatter config: mechanically enforced rules do not need manual standards.
# (None exist in this repo today — verify, in case one was added since.)
cat .eslintrc* eslint.config.* .prettierrc* 2>/dev/null
Phase 2: Classify current state
Determine which of these states applies. More than one may apply.
| State | Condition | Action |
|---|---|---|
| Proper | docs/coding-standards.md exists AND CLAUDE.md has a reference to it |
Score for gaps only; proceed to Phase 3 |
| Missing | No standards found anywhere | Create docs/coding-standards.md from scratch; proceed to Phase 3 |
| Inline | Standards are written directly inside CLAUDE.md (not just a reference line) | Copy into docs/coding-standards.md in Phase 4, keeping enforcement-critical rules inline |
| Scattered | Standards exist in docs/LOGGING.md, docs/TESTING.md, or other files | Consolidate into docs/coding-standards.md; note source files in Phase 5 |
| Incomplete | docs/coding-standards.md exists but scoring reveals gaps |
Fill gaps; proceed to Phase 3 |
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.
- yesterday First seen · 242 lines · 153 tokens per session scan A 76cdffe17adc
coding-standards-auditor is an agent published in the GitHub repository agigante80/Actual-sync (12 stars, last pushed 3d ago), licensed MIT. It adds 153 tokens to every session and 3,058 once invoked, about $0.0008 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 2026-09-04.
Other agents, from other repositories
kastell-auditor
Security audit analyzer for Kastell servers. Runs kastell audit, maps results across 5 security domains (perimeter, authentication, runtime, internals, compliance), tracks score trends across sessions. Use when running kastell audit, analyzing server security posture, investigating audit findings, or generating…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.