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 skills add gustavobarbosab/sage --skill skillgit 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/skills/gustavobarbosab/sage/skill)<a href="https://agentmods.dev/skills/gustavobarbosab/sage/skill"><img src="https://agentmods.dev/badge/skills/gustavobarbosab/sage/skill/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/skills/gustavobarbosab/sage/skill"><img src="https://agentmods.dev/badge/skills/gustavobarbosab/sage/skill.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 | $0.00122 | $0.01111 |
| Opus 5.5 | $0.00049 | $0.00444 |
| Sonnet 5.5 | $0.00024 | $0.00222 |
| Haiku 4.5 | $0.00012 | $0.00111 |
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 2mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- sage — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 93 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 | Output |
|---|---|---|---|
/sage spec <description> |
Feature description, ticket text, or idea | references/spec.md |
Interview → spec.md + behavior.md |
/sage behavior |
(none — reads spec.md) | references/behavior.md |
behavior.md (standalone regeneration) |
/sage code |
(none — reads spec.md + behavior.md) | references/code.md |
Implementation files |
/sage update <feedback> |
Precise feedback tied to spec or behavior | references/update.md |
Updated files |
/sage pr |
(none — reads full context) | references/pr.md |
pr.md |
/sage doc |
(none — reads full context) | references/doc.md |
doc.md |
/sage harness init |
(none — interactive wizard) | references/harness-init.md |
.sage/harness.md |
/sage harness generate |
(none — reads codebase files) | references/harness-generate.md |
.sage/harness.md |
/sage harness review |
(none — reads harness.md) | references/harness-review.md |
Review report |
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.
Special flow for /sage spec
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .DS_Store 6.0 KB
- chatgpt/custom-gpt-instructions.md 5.1 KB
- chatgpt/harness.template.md 661 B
- chatgpt/README.md 1.4 KB
- claude-code/.claude/commands/sage.md 3.9 KB
- claude-code/.claude/commands/sage/behavior.md 2.6 KB
- claude-code/.claude/commands/sage/code.md 1.6 KB
- claude-code/.claude/commands/sage/doc.md 1.4 KB
- claude-code/.claude/commands/sage/harness-generate.md 1.6 KB
- claude-code/.claude/commands/sage/harness-init.md 1.9 KB
- claude-code/.claude/commands/sage/harness-review.md 1.4 KB
- claude-code/.claude/commands/sage/pr.md 1.4 KB
- claude-code/.claude/commands/sage/spec.md 4.6 KB
- claude-code/.claude/commands/sage/update.md 1.7 KB
- claude-code/README.md 1.3 KB
- claude/README.md 1.1 KB
- claude/references/behavior.md 2.6 KB
- claude/references/code.md 1.6 KB
- claude/references/doc.md 1.4 KB
- claude/references/harness-generate.md 1.6 KB
- claude/references/harness-init.md 1.9 KB
- claude/references/harness-review.md 1.4 KB
- claude/references/pr.md 1.4 KB
- claude/references/spec.md 4.6 KB
- claude/references/update.md 1.7 KB
- claude/sage.skill 13 KB
- claude/SKILL.md 4.6 KB
- copilot/.github/copilot-instructions.md 3.4 KB
- copilot/.github/prompts/sage-behavior.prompt.md 2.7 KB
- copilot/.github/prompts/sage-code.prompt.md 1.7 KB
- copilot/.github/prompts/sage-doc.prompt.md 1.5 KB
- copilot/.github/prompts/sage-pr.prompt.md 1.5 KB
- copilot/.github/prompts/sage-spec.prompt.md 4.7 KB
- copilot/.github/prompts/sage-update.prompt.md 1.8 KB
- copilot/.sage/harness.md 601 B
- copilot/README.md 1.6 KB
- cursor/.cursor/rules/sage-behavior.mdc 2.7 KB
- cursor/.cursor/rules/sage-code.mdc 1.7 KB
- cursor/.cursor/rules/sage-doc.mdc 1.5 KB
- cursor/.cursor/rules/sage-harness-generate.mdc 1.8 KB
- cursor/.cursor/rules/sage-harness-init.mdc 2.1 KB
- cursor/.cursor/rules/sage-harness-review.mdc 1.5 KB
- cursor/.cursor/rules/sage-pr.mdc 1.5 KB
- cursor/.cursor/rules/sage-spec.mdc 4.7 KB
- cursor/.cursor/rules/sage-update.mdc 1.8 KB
- cursor/.cursor/rules/sage.mdc 1.2 KB
- cursor/.cursorrules 3.8 KB
- cursor/.sage/harness.md 605 B
- cursor/README.md 1.7 KB
- generic/harness.template.md 633 B
- generic/README.md 1.4 KB
- generic/sage-session-prompt.md 2.7 KB
- README.md 5.4 KB
- references/behavior.md 2.6 KB
- references/code.md 1.6 KB
- references/doc.md 1.4 KB
- references/harness-generate.md 1.6 KB
- references/harness-init.md 1.9 KB
- references/harness-review.md 1.4 KB
- references/pr.md 1.4 KB
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.
- 2mo ago First seen · 93 lines · 122 tokens per session scan A c31ab0352a62
sage is a skill published in the GitHub repository gustavobarbosab/sage (2 stars, last pushed 4mo ago), licensed MIT. It adds 122 tokens to every session and 1,111 once invoked, about $0.0005 per session on Opus 5.5. 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 skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.