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/sagegit 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)<a href="https://agentmods.dev/commands/gustavobarbosab/sage/sage"><img src="https://agentmods.dev/badge/commands/gustavobarbosab/sage/sage.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 | $0.00122 | $0.00955 |
| Opus 5 | $0.00061 | $0.00477 |
| Sonnet 5 | $0.00024 | $0.00191 |
| Haiku 4.5 | $0.00012 | $0.00096 |
Grade A, and why
sage 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 5d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SAGE
Spec · Assert · Generate · Export
A spec-first workflow that combines SDD, BDD, and Harness Engineering to front-load thinking and back-load generation.
spec.md → behavior.md → code → pr.md + doc.md
(you) (you + AI) (you + AI) (AI + you)
Commands
The user interacts with SAGE using /sage <command> [argument].
| Command | Argument | Reference file |
|---|---|---|
/sage spec <description> |
Feature description, ticket text, or idea | references/spec.md |
/sage behavior |
(none — reads spec.md) | references/behavior.md |
/sage code |
(none — reads spec.md + behavior.md) | references/code.md |
/sage update <feedback> |
Precise feedback tied to spec or behavior | references/update.md |
/sage pr |
(none — reads full context) | references/pr.md |
/sage doc |
(none — reads full context) | references/doc.md |
/sage harness init |
(none — interactive wizard) | references/harness-init.md |
/sage harness generate |
(none — reads codebase files) | references/harness-generate.md |
/sage harness review |
(none — reads harness.md) | references/harness-review.md |
How to handle each command
When the user types a /sage command:
- Identify the sub-command from the table above
- Read the corresponding reference file — it contains the full prompt and instructions for that step
- Extract the inline argument if provided (e.g.
/sage spec "Login screen with email and password"→ argument is"Login screen with email and password") - Execute the step following the reference file instructions
If the user types /sage with no sub-command, show the command table above and ask which step they want to run.
Prerequisite — the harness
Before running any SAGE step, check if .sage/harness.md (or CLAUDE.md, .cursorrules, or project knowledge) exists.
- If it exists — load it as context for all steps
- If it doesn't exist — remind the user once: "No harness found. Run
/sage harness initor/sage harness generateto set one up. I'll proceed without it for now." Then continue.
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.
- 5d ago First seen · 84 lines · 122 tokens per session scan A 35e3b3e975ea
sage is a command published in the GitHub repository gustavobarbosab/sage (2 stars, last pushed 2mo ago), licensed MIT. It adds 122 tokens to every session and 955 once invoked, about $0.0006 per session on Opus 5. 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.