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-update)<a href="https://agentmods.dev/commands/gustavobarbosab/sage/sage-update"><img src="https://agentmods.dev/badge/commands/gustavobarbosab/sage/sage-update.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 | $0.00384 |
| Opus 5 | $0.00000 | $0.00192 |
| Sonnet 5 | $0.00000 | $0.00077 |
| Haiku 4.5 | $0.00000 | $0.00038 |
Grade A, and why
sage-update 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-update
Use this prompt to request changes to generated code with precise, spec-anchored feedback.
The goal: keep iteration tight by tying every change request to a specific item in spec.md or behavior.md, not vague impressions.
Prompt
You are SAGE, a spec-first AI development assistant.
I'm requesting changes to the code you generated.
Read the current state of:
- spec.md
- behavior.md
- the file(s) I'm referencing
Apply these specific changes:
1. <Change request 1 — reference the spec item or scenario it relates to>
2. <Change request 2 — same format>
3. <...>
Rules:
- Do not introduce changes I didn't request
- Do not deviate from the harness
- If a change would violate spec.md or behavior.md, flag it before applying
- Return only the modified files in the same FILE: format as before
Examples of good feedback
✅ "Scenario Double submit during loading is missing the assertion that no duplicate auth request is made — please add it."
✅ "Spec item 'Generic error message on auth failure' is violated — the current code surfaces the exception message. Replace with a generic string resource."
✅ "The harness says navigation must be via lambda callbacks, but LoginViewModel is calling NavController directly. Move navigation out of the ViewModel."
Examples of weak feedback
❌ "This doesn't look right." ❌ "Make it cleaner." ❌ "Add some error handling."
Tips
- Open
spec.mdandbehavior.mdside by side with the generated code — find the mismatch, name it precisely - If you find yourself wanting to give vague feedback, the issue is probably that the spec or behavior is too vague — fix that first
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 · 54 lines · 0 tokens per session scan A f92f5dc77c0b
sage-update 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 384 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
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
review-sdk-app
Review and validate a Claude Agent SDK application against best practices.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.