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/gustavobarbosab/sageWrote 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/commands/gustavobarbosab/sage/sage-harness-generate)<a href="https://agentmods.dev/commands/gustavobarbosab/sage/sage-harness-generate"><img src="https://agentmods.dev/badge/commands/gustavobarbosab/sage/sage-harness-generate/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.
<a href="https://agentmods.dev/commands/gustavobarbosab/sage/sage-harness-generate"><img src="https://agentmods.dev/badge/commands/gustavobarbosab/sage/sage-harness-generate.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00622 |
| Opus 5 | $0.00000 | $0.00311 |
| Sonnet 5 | $0.00000 | $0.00124 |
| Haiku 4.5 | $0.00000 | $0.00062 |
Grade A, and why
sage-harness-generate 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 10d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sage-harness-generate
Use this prompt to let AI infer a harness.md from your existing codebase.
This is the fastest way to onboard SAGE into an existing project — point the AI at your code and let it extract the conventions you've already established.
Prompt
You are SAGE, a spec-first AI development assistant.
I'll share several files from my codebase. Analyze them and generate a harness.md
that captures:
- Tech stack and versions (from build files, package manifests, lockfiles)
- Architecture patterns in use (MVI, MVVM, Clean Architecture, etc.)
- Naming conventions (ViewModel suffixes, file organization, package structure)
- Dependency injection approach
- State management patterns
- Navigation approach
- Test framework and naming patterns
- Patterns that appear to be deliberately avoided
Format the output as:
## Project Harness — <inferred project name>
### Stack
- Bullet list
### Conventions
- Naming patterns with examples from the code
- Architecture rules
### Avoid
- Anti-patterns NOT found in the code (i.e. things the team has avoided)
- Deprecated APIs not used
Flag anything that seems inconsistent across files with:
⚠️ Inconsistency: <description>
Where you're inferring something with low confidence, mark it:
❓ Possibly: <inferred rule> — confirm before adopting
I will paste the files now. After you've analyzed them, generate the harness.
Files to share
The most useful files to feed the AI:
build.gradle.kts/build.gradle/package.json/pyproject.toml(stack and versions)- 2-3
ViewModelor equivalent state-holding classes (architecture patterns) - 2-3 UI files / screens / components (UI conventions)
- 1-2 DI modules (injection approach)
- 1-2 test files (test conventions)
- Any existing
.editorconfig,.cursorrules,CLAUDE.md, or style guide
Don't include secrets, generated code, or massive files — the AI just needs enough context to infer patterns.
After generation
- Review the inferred harness carefully — AI is good at pattern recognition but can miss intent
- Resolve every ⚠️ inconsistency — decide which version is the actual convention
- Confirm every ❓ possibly — these are guesses
- Save to your tool's expected location (see sage-harness-init.md for paths)
- Run
/sage-harness-reviewperiodically to catch drift over time
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.
- 10d ago First seen · 81 lines · 0 tokens per session scan A 5d0235b42556
sage-harness-generate 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 622 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.