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/docgit 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 | $0.00344 |
| Opus 5 | $0.00000 | $0.00172 |
| Sonnet 5 | $0.00000 | $0.00069 |
| Haiku 4.5 | $0.00000 | $0.00034 |
Grade A, and why
doc 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 doc
Generates doc.md — a behavioral reference document for the feature with ADR-style decisions embedded.
Instructions
Read:
spec.mdbehavior.md- The generated code files
pr.mdif it exists
Generate doc.md with this structure:
## <FeatureName> — Behavior Reference
### Supported states
- <State>: <When it occurs — 1 line>
### Validation rules
- <Field>: <Rule and exact trigger condition>
### Edge cases
- <Edge case>: <Expected behavior>
### Decisions
- <Decision made during SAGE workflow>
→ <The reasoning — the WHY, not just the WHAT>
### Out of scope
- <What this feature deliberately does NOT handle>
### Known limitations
- <Current limitation or future improvement>
Rules
- Each item should be 1–2 lines — the goal is a document a teammate scans in 60 seconds
- The "Decisions" section is the most valuable long-term — it captures reasoning that would otherwise be lost
- Every resolved open question from behavior.md must appear as a Decision entry
- Omit empty sections rather than padding with placeholders
- Focus on behavior, not implementation details (those belong in code comments)
After generation
Tell the user: "doc.md is ready. You can publish it to:
- Commit alongside the code in your repo
- Confluence via Atlassian MCP
- Notion via Notion MCP
- Obsidian vault — drop the file in directly
- GitHub Wiki via
gh api"
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 · 59 lines · 0 tokens per session scan A 791ce39ad12f
doc 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 344 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.