sage-harness-review

sage-harness-review is a command for Claude Code from gustavobarbosab/sage. It costs 0 tokens per session (433 once invoked), scanned A, original, MIT.

A review command for checking a project's harness.md, a file that tells an AI coding assistant which conventions to follow.

In plain words
What is it for?
Run it during regular maintenance, after a major refactor, or when the assistant starts producing inconsistent results. It reports specific issues and suggested fixes.
Why use it?
It finds unclear rules, contradictions, missing guidance, outdated practices, and other causes of inconsistent AI-generated code.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Good fit Run it during regular maintenance, after a major refactor, or when the assistant starts producing inconsistent results. It reports specific issues and suggested fixes.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/gustavobarbosab/sage/sage-harness-review"><img src="https://agentmods.dev/badge/commands/gustavobarbosab/sage/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 433 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 $0.00433
Opus 5 $0.00000 $0.00217
Sonnet 5 $0.00000 $0.00087
Haiku 4.5 $0.00000 $0.00043

Measured 11d ago against content hash e4498c04956c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

sage-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 11d 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.

commands/sage-harness-review.md · 62 lines

What it actually says

/sage-harness-review

Use this prompt to audit your current harness.md for drift, gaps, or inconsistencies.

Harnesses get stale. Conventions evolve. This command catches the mismatch.


Prompt

You are SAGE, a spec-first AI development assistant.

Review the harness.md I'll provide 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 common categories (e.g. testing, error handling, navigation)
4. Outdated stack versions or deprecated patterns
5. Anything that would cause inconsistent AI output

For each issue found, format as:
⚠️ <Issue> → <Suggested fix>

Also flag opportunities to strengthen the harness:
💡 <Suggestion> → <Why it would help>

Be specific. Don't tell me "improve naming conventions" — tell me which convention
is unclear and what concrete rule would fix it.

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

When to run this

  • Every quarter — convention drift is inevitable in active projects
  • After a major refactor — your old harness may now describe patterns you've abandoned
  • When you notice AI output drifting — if generated code keeps missing a convention, the harness probably doesn't enforce it strongly enough
  • Before onboarding a new team member — fresh eyes on the harness reveal what's actually documented vs assumed

After review

For each ⚠️:

  • Decide whether to update the harness, update the code, or both
  • Commit the harness change with a brief explanation in the message

For each 💡:

  • Treat as optional — add if it would genuinely strengthen the AI's output
  • Skip if it would over-constrain without clear benefit

Tips

  • A harness with no issues is rare and often a sign you've stopped iterating
  • Don't add rules just because the AI flagged them — every rule has a maintenance cost
  • The best harnesses are short and decisive, not long and exhaustive
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. 11d ago First seen · 62 lines · 0 tokens per session scan A e4498c04956c

Subscribe to this mod's changes

sage-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 433 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.