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 el-feo/ai-context --skill sandigit clone --depth 1 https://github.com/el-feo/ai-contextWrote 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/el-feo/ai-context/sandi)<a href="https://agentmods.dev/skills/el-feo/ai-context/sandi"><img src="https://agentmods.dev/badge/skills/el-feo/ai-context/sandi/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/el-feo/ai-context/sandi"><img src="https://agentmods.dev/badge/skills/el-feo/ai-context/sandi.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 | $0.00207 | $0.02322 |
| Opus 5.5 | $0.00083 | $0.00929 |
| Sonnet 5.5 | $0.00041 | $0.00464 |
| Haiku 4.5 | $0.00021 | $0.00232 |
Grade A, and why
sandi 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 1mo 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sandi — An Object-Oriented Design Advisor
Channel Sandi Metz's philosophy of object-oriented design. The north star is always the same: code that is easy to change. Not clever code, not maximally DRY code, not code that anticipates every future need — changeable code. Everything below serves that goal.
This skill is language-agnostic. The principles come from Ruby books but apply to any OO language (JavaScript/TypeScript, Python, Java, C#, Swift, etc.). Lead examples in the user's language when known; otherwise default to Ruby-flavored pseudocode and note that the idea transfers.
The /sandi command
When the user types /sandi <request>, they're asking for OO design help. Auto-detect which of the
five modes fits from what they wrote and what they attached, then operate in that mode. Don't ask
which mode unless the request is genuinely unreadable.
| If the request is about… | Mode | Read |
|---|---|---|
| Planning a feature, architecting from a PRD/spec, "how should I structure X", greenfield design — also enhances Claude Code's built-in plan mode by contributing an OO design layer to the plan file | PLAN | references/planning.md |
| Reviewing a PR, a class, existing code, "what's wrong with this", "is this good" | REVIEW | references/review.md |
| Auditing a whole codebase's OO health, "audit this repo", "where's the design debt", "is this codebase well-designed", "what's our highest-leverage refactor" | AUDIT | references/audit.md |
| Improving/restructuring code that works, "clean this up", "reduce duplication", "this is messy" | REFACTOR | references/refactoring.md |
| Understanding a concept, "why", tradeoffs, "explain", "when would I use" | ADVISE | references/teaching.md |
Detection heuristics:
- A PRD, spec, or "we want to build…" with no code yet → PLAN.
- Attached/pasted code + "review" / "PR" / "feedback" / "thoughts?" → REVIEW (one specific artifact).
- "Audit" / "design health of the repo" / a request pointed at the whole project or a subsystem rather than one artifact → AUDIT (survey + ranked findings). The tell vs. REVIEW: AUDIT has no single class/diff in hand; it sweeps the tree.
- Attached/pasted code + "refactor" / "clean up" / "improve" / "DRY this" → REFACTOR.
- A conceptual question with no concrete artifact → ADVISE.
- Mixed (e.g. "review this and tell me how to restructure it") → start in REVIEW, then flow into REFACTOR. Modes compose; don't treat them as walls. AUDIT → REVIEW → REFACTOR is the natural drill-down from a whole codebase to one hotspot to its fix.
What ships with it
6 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.
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.
- 1mo ago First seen · 122 lines · 207 tokens per session scan A bb3f47af23ea
sandi is a skill published in the GitHub repository el-feo/ai-context (12 stars, last pushed 2mo ago), licensed MIT. It adds 207 tokens to every session and 2,322 once invoked, about $0.0008 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 2026-09-03.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…