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.
npx agentmods add commands/gustavobarbosab/sage/updategit clone --depth 1 https://github.com/gustavobarbosab/sageWhat 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 | $0.00000 | $0.00392 |
| Opus 5 | $0.00000 | $0.00196 |
| Sonnet 5 | $0.00000 | $0.00078 |
| Haiku 4.5 | $0.00000 | $0.00039 |
Grade A, and why
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 2d 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
Applies precise, spec-anchored feedback to generated code.
Inline argument
The user provides feedback inline:
/sage update "Scenario 'Double submit' is missing the assertion that no duplicate request is made"
/sage update "spec item 4 violated — navigation is inside the ViewModel, move it out"
/sage update "harness says Material3 only but the code imports Material2 Button"
If no argument is provided, ask: "What needs changing? Tie your feedback to a specific spec item or scenario."
Instructions
Read the feedback argument. Apply the requested changes to the relevant files.
Rules:
- Do NOT introduce changes the user didn't request
- Do NOT deviate from the harness
- If a requested change would violate spec.md or behavior.md, flag it before applying: "⚠️ This change conflicts with [spec item / scenario]. Do you want to update the spec first?"
- Return only the modified files in the same
// FILE:format
What good feedback looks like
Guide the user toward precise feedback if theirs is vague:
✅ "Scenario Double submit during loading is missing the assertion that no duplicate auth request is made"
✅ "Spec item 'Generic error on auth failure' is violated — raw exception message is surfaced. Replace with a generic string resource."
✅ "Harness says navigation via lambda callbacks but LoginViewModel calls NavController directly."
❌ "This doesn't look right" → ask: "Which spec item or scenario does it violate?" ❌ "Make it cleaner" → ask: "What specifically should change?"
After update
Tell the user:
"Changes applied. Review the updated files. Run /sage update <feedback> again for further changes, or /sage pr and /sage doc when ready to export."
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.
- 2d ago First seen · 48 lines · 0 tokens per session scan A b83a6b664f19
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 392 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
git
Git operations with intelligent commit messages and workflow optimization.
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.