harness-compliance-reviewer

harness-compliance-reviewer is an agent for Claude Code from ItamarZand88/CLI-Anything-WEB. It costs 80 tokens per session (1,940 once invoked), scanned B, original, MIT.

A code-review agent for checking a command-line tool against a shared set of coding conventions. It reads the source code and scores issues in areas such as errors, authentication, client design, command patterns, and JSON response structure.

In plain words
What is it for?
Use it to review a generated CLI's source code, identify and score compliance findings, and skip checks that do not apply to the site's profile.
Why use it?
It finds convention violations before they become maintenance or compatibility problems. It also separates code-structure checks from checks that require running the tool.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

Part of the cli-anything-web plugin — 6 skills, 6 commands, 4 agents, 1 MCP server shipped together

Good fit Use it to review a generated CLI's source code, identify and score compliance findings, and skip checks that do not apply to the site's profile.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/itamarzand88/cli-anything-web/harness-compliance-reviewer
Install

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.

Clone the repo
git clone --depth 1 https://github.com/ItamarZand88/CLI-Anything-WEB

Made for: Claude Code.

Or install cli-anything-web, the plugin that ships this one along with the rest of its 6 skills, 6 commands, 4 agents, 1 MCP server.

Wrote 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.

agentmods badge for harness-compliance-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/itamarzand88/cli-anything-web/harness-compliance-reviewer/github.svg)](https://agentmods.dev/agents/itamarzand88/cli-anything-web/harness-compliance-reviewer)
Your own site
<a href="https://agentmods.dev/agents/itamarzand88/cli-anything-web/harness-compliance-reviewer"><img src="https://agentmods.dev/badge/agents/itamarzand88/cli-anything-web/harness-compliance-reviewer/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.

agentmods 80×15 button for harness-compliance-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/itamarzand88/cli-anything-web/harness-compliance-reviewer"><img src="https://agentmods.dev/badge/agents/itamarzand88/cli-anything-web/harness-compliance-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,940 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00080 $0.01940
Opus 5 $0.00040 $0.00970
Sonnet 5 $0.00016 $0.00388
Haiku 4.5 $0.00008 $0.00194

Measured 12d ago against content hash 53f0dc6ab19a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

harness-compliance-reviewer scanned grade B with 1 finding 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 12d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- Credentials stored with `chmod 600`
cli-anything-web-plugin/agents/harness-compliance-reviewer.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HARNESS Compliance Reviewer

You are reviewing a generated CLI to verify it follows all conventions defined in skills/shared/CONVENTIONS.md and the quality checklist — not just structurally, but in actual code logic.

Inputs: You will receive APP_PATH, APP_NAME, and site profile (auth_type, is_read_only).

Site Profile Awareness

Before scoring, determine the site profile:

  • No-auth sites: Skip all auth-related checks (auth.py, auth commands, cookie priority, auth retry). Do NOT report missing auth features as findings.
  • Read-only sites: Skip write operation checks.
  • No-RPC sites: Skip batchexecute/RPC-specific checks.

Mark skipped checks as N/A, not as findings.

Scope Boundary

You own: code quality and convention compliance ONLY — verified by READING source code, not by running the CLI.

JSON envelope division of labor (explicit):

  • You own the envelope STRUCTURE check: the code defines the correct {"success": true, "data": ...} / {"error": true, "code", "message"} shapes — to_dict() implementations, json_success()/json_error() helpers, handle_errors() wiring, no click.ClickException bypass.
  • output-ux-reviewer owns end-to-end output VALIDITY: it RUNS commands and checks that actual --json output parses, contains no protocol leaks (wrb.fr, af.httprm, empty []), and that REPL UX works. Do NOT run commands to inspect live output — report structural defects only.

Do NOT report API coverage issues (that's traffic-fidelity-reviewer). Do NOT report UX/runtime-output issues (that's output-ux-reviewer).

Your Task

  1. Find and read the conventions spec by globbing for **/cli-anything-web-plugin/skills/shared/CONVENTIONS.md — it is the single source of truth for every rule below (HARNESS.md only indexes it).
  2. Find and read the quality checklist by globbing for **/cli-anything-web-plugin/skills/standards/references/quality-checklist.md.
  3. Read all source files in {APP_PATH}/agent-harness/cli_web/{app}/.
  4. Check each applicable convention against the actual implementation.

Read the full file on GitHub · 147 lines

Changes

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.

  1. 12d ago First seen · 147 lines · 80 tokens per session scan B 53f0dc6ab19a

Subscribe to this mod's changes

harness-compliance-reviewer is an agent published in the GitHub repository ItamarZand88/CLI-Anything-WEB (217 stars, last pushed 11d ago), licensed MIT. It adds 80 tokens to every session and 1,940 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

ia-kieran-reviewer

Persona-driven line-level Python and TypeScript code review with extremely high bar for type safety, naming conventions, and modern patterns. Use for line-level Py/TS quality after PR implementation. For broader review workflow, use the code-review skill.

iliaal/whetstone · 54 tokens

python-reviewer

Python-specific code reviewer focusing on type safety, PEP 8 compliance, and Python best practices. Use after implementing Python code to catch Python-specific issues.

DmitriyYukhanov/claude-plugins · 35 tokens

skeptic

Adversarial verifier for a single review finding. Given one claimed issue plus the code, tries to refute it against reality to cut false positives. Use to verify findings before they are reported. Read-only. Also cross-checks a single research claim against its cited web sources and sibling claims (structural…

restarter/lets-workflow · 72 tokens

actor

Meta-agent that adopts external personalities and adapts them to LETS modes. Loads identity from personality text provided in prompt, then operates as that persona with LETS structured output.

restarter/lets-workflow · 37 tokens

architect

System design expert for architecture reviews, pattern analysis, SOLID principles evaluation, and coupling/abstraction assessments. Use when reviewing structural changes, evaluating design decisions, or analyzing system architecture.

restarter/lets-workflow · 39 tokens

backend

Backend development expert for API design review, business logic analysis, error handling assessment, and performance evaluation. Use when reviewing server-side code, API endpoints, data processing, or service integrations.

restarter/lets-workflow · 39 tokens