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/harness-generate)<a href="https://agentmods.dev/commands/gustavobarbosab/sage/harness-generate"><img src="https://agentmods.dev/badge/commands/gustavobarbosab/sage/harness-generate.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 | $0.00000 | $0.00403 |
| Opus 5 | $0.00000 | $0.00201 |
| Sonnet 5 | $0.00000 | $0.00081 |
| Haiku 4.5 | $0.00000 | $0.00040 |
Grade A, and why
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 7d 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.
What it actually says
/sage harness generate
Infers .sage/harness.md by analyzing existing codebase files.
Instructions
Ask the user to share files from their codebase. Suggest the most useful ones:
"Please share some files so I can infer your project conventions. The most useful are:
build.gradle.kts/package.json/pyproject.toml(stack and versions)- 2–3 ViewModel or 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, orCLAUDE.md"
Once files are provided, analyze them and generate .sage/harness.md:
## Project Harness — <inferred project name>
### Stack
- <inferred stack items with versions>
### Conventions
- <naming patterns with examples from the code>
- <architecture rules>
### Avoid
- <patterns NOT found in the code — things deliberately avoided>
Flags to include
Mark inferences with low confidence:
❓ Possibly: <inferred rule> — confirm before adopting
Mark inconsistencies found across files:
⚠️ Inconsistency: <description> — which version is correct?
Rules
- Only infer what the code actually shows — don't invent conventions
- The "Avoid" section will be sparse on first generation — that's expected
- Always flag ❓ and ⚠️ items for the user to resolve before committing
After generation
Tell the user:
"Harness drafted at .sage/harness.md. Review every ❓ and ⚠️ item before committing. Run /sage harness review after any major refactor to keep it accurate."
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.
- 7d ago First seen · 61 lines · 0 tokens per session scan A c868162b76d4
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 403 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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.