harness-review

harness-review is a command for Claude Code from gustavobarbosab/sage. It costs 0 tokens per session (326 once invoked), scanned A, original, MIT.

A command that reviews .sage/harness.md, a project guide containing rules for an AI coding assistant. It looks for unclear, conflicting, missing, outdated, or inconsistent guidance.

In plain words
What is it for?
Reviewing project coding rules, identifying gaps in areas such as errors, navigation, tests, and text resources, and suggesting specific corrections.
Why use it?
It finds instructions that may lead to inconsistent code or cannot be checked during review.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

Good fit Reviewing project coding rules, identifying gaps in areas such as errors, navigation, tests, and text resources, and suggesting specific corrections.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/gustavobarbosab/sage/harness-review
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/gustavobarbosab/sage

Made for: Claude Code.

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-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/gustavobarbosab/sage/harness-review/github.svg)](https://agentmods.dev/commands/gustavobarbosab/sage/harness-review)
Your own site
<a href="https://agentmods.dev/commands/gustavobarbosab/sage/harness-review"><img src="https://agentmods.dev/badge/commands/gustavobarbosab/sage/harness-review/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-review

Your own site · 80×15
<a href="https://agentmods.dev/commands/gustavobarbosab/sage/harness-review"><img src="https://agentmods.dev/badge/commands/gustavobarbosab/sage/harness-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 326 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00000 $0.00326
Opus 5 $0.00000 $0.00163
Sonnet 5 $0.00000 $0.00065
Haiku 4.5 $0.00000 $0.00033

Measured 9d ago against content hash 73faf4134b1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

harness-review 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 9d 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.

skill/claude-code/.claude/commands/sage/harness-review.md · 42 lines

What it actually says

/sage harness review

Audits the current .sage/harness.md for drift, gaps, or inconsistencies.

Instructions

Read .sage/harness.md (or CLAUDE.md, .cursorrules, or project knowledge).

Analyze for:

  1. Vague or unenforceable rules — rules that can't be checked in code review
  2. Conflicting conventions — rules that contradict each other
  3. Missing categories — common gaps: error handling, navigation, testing, string resources
  4. Outdated stack versions — deprecated patterns or libraries
  5. Anything that would cause inconsistent AI output — ambiguous rules

Format issues as:

⚠️ <Issue> → <Suggested fix>

Format improvement suggestions as:

💡 <Suggestion> → <Why it would help AI output quality>

If the harness is solid, say so explicitly. Don't manufacture issues.


Rules

  • Be specific — "improve naming conventions" is not useful; "the ViewModel naming rule doesn't specify whether test files use Test or Spec suffix" is
  • Don't suggest rules just because they're common — every rule has a maintenance cost
  • The best harnesses are short and decisive, not long and exhaustive

After review

Tell the user: "Review complete. For each ⚠️ — decide whether to update the harness, update the code, or both, and commit the change with a brief message. 💡 suggestions are optional — add only what genuinely improves AI output."

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. 9d ago First seen · 42 lines · 0 tokens per session scan A 73faf4134b1c

Subscribe to this mod's changes

harness-review is a command published in the GitHub repository gustavobarbosab/sage (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 326 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 2026-08-31.