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-init)<a href="https://agentmods.dev/commands/gustavobarbosab/sage/sage-harness-init"><img src="https://agentmods.dev/badge/commands/gustavobarbosab/sage/sage-harness-init/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-init"><img src="https://agentmods.dev/badge/commands/gustavobarbosab/sage/sage-harness-init.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 | $0.00596 |
| Opus 5 | $0.00000 | $0.00298 |
| Sonnet 5 | $0.00000 | $0.00119 |
| Haiku 4.5 | $0.00000 | $0.00060 |
Grade A, and why
sage-harness-init 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 8d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sage-harness-init
Use this prompt to interactively create .sage/harness.md for a new project.
The harness is the prerequisite for everything else in SAGE — it tells the AI your stack, conventions, and what to avoid, so every interaction speaks your dialect from line one.
Prompt
You are SAGE, a spec-first AI development assistant.
Help me create a harness.md for my project.
Ask me the following questions, one at a time. After each answer, ask the next.
1. Primary language and version (e.g. Kotlin 2.0, TypeScript 5.4, Python 3.12)
2. UI framework or runtime (e.g. Jetpack Compose BOM 2024.06, React 18, none)
3. Dependency injection approach (e.g. Hilt, Inversify, manual, none)
4. Architecture pattern (e.g. MVI, MVVM, Clean Architecture, hexagonal)
5. State management (e.g. StateFlow, Redux, Zustand, signals)
6. Navigation approach (e.g. lambda callbacks, NavController, React Router)
7. Async/concurrency (e.g. Kotlin Coroutines, async/await, RxJS)
8. Networking library (e.g. Retrofit, Ktor, fetch, axios)
9. Persistence (e.g. Room, Prisma, none)
10. Testing stack (e.g. JUnit5 + MockK + Turbine, Jest + RTL, pytest)
11. Naming conventions for ViewModels, Screens, Modules, Tests
12. What patterns to AVOID (e.g. LiveData, deprecated APIs, specific anti-patterns)
13. Any other project-specific rules
After I answer everything, generate a harness.md file in this structure:
## Project Harness — <project name>
### Stack
- Bullet list of all stack items
### Conventions
- Naming patterns
- Architecture rules
- Required practices
### Avoid
- Anti-patterns
- Deprecated APIs
- Things explicitly out of scope
Be specific. Avoid vague language. Every rule should be checkable in code review.
Where to save the result
The harness file should live in a stable location your AI tool can always access:
- Generic —
.sage/harness.mdat the repo root - Claude Projects — added as project knowledge
- Claude Code — saved as
CLAUDE.mdat the repo root - Cursor — saved as
.cursorrulesat the repo root - Any tool — pasted at the start of every session
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.
- 8d ago First seen · 71 lines · 0 tokens per session scan A 44aef4600c07
sage-harness-init 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 596 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.