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 skills/silo-code/silo/silo-testingnpx skills add silo-code/silo --skill silo-testinggit clone --depth 1 https://github.com/silo-code/siloWhat 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 | $0.00065 | $0.00486 |
| Opus 5 | $0.00032 | $0.00243 |
| Sonnet 5 | $0.00013 | $0.00097 |
| Haiku 4.5 | $0.00006 | $0.00049 |
Grade A, and why
silo-testing 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 yesterday.
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
Testing in Silo
Every change that adds or changes behavior ships with unit tests in the same
change. Tests are part of the work, not a follow-up. Don't mark a task done
until pnpm test is green with coverage for what you added.
How testing works here:
- Vitest, co-located. Put
*.test.ts/*.test.tsxnext to the source it covers; the packagevitest.config.tspicks upsrc/**/*.{test,spec}.{ts,tsx}. Run everything withpnpm test, or one package withpnpm --filter <pkg> exec vitest run <path>. - Pure-logic style. The suite tests logic, not rendered React
(
@testing-library/reactis intentionally not a dependency). When the logic you're adding lives inside a component, extract it into a pure, exported helper and test that — e.g.view-switcher-model.ts(switcher show/segmented/ dropdown rules),markdown-preview/menu.ts(context-menu enablement), andmarkdown-preview/match.ts(file matching) were factored out of their components precisely so the rules are unit-testable. Components stay thin glue. - Host state can be driven directly: set up
store(the valtio proxy) and the relevant registries inbeforeEach, exercise the service, assert on the store — seeeditor-service.test.tsandeditor-registry.test.ts. - Cover the contract and the edges, not just the happy path: fallbacks,
no-ops/guards, disabled states, and "hidden/absent" cases (the editor
view-switching tests pin the priority tie-break, stale-
viewTypefallback, read-only Cut/Paste, and the single-view/diff/untitled hidden cases).
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.
- yesterday First seen · 32 lines · 65 tokens per session scan A b2ade918a5f2
silo-testing is a skill published in the GitHub repository silo-code/silo (53 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 486 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
agtx-sweep
Sweep this conversation into agtx tasks and push them to the kanban board. Use when the user wants to capture, decompose, or hand off conversation results to the agtx board.
agtx-execute
Execute an approved implementation plan. Implement the changes, then write a summary to .agtx/execute.md and stop.
agtx-plan
Plan a task implementation. Analyze the codebase, create a detailed plan, write it to .agtx/plan.md, then stop and wait for user approval before making any changes.
agtx-research
Explore the codebase to understand a task before planning. Write findings to .agtx/research.md and stop. This is a read-only exploration — do not modify any files.
agtx-brainstorm
Enter brainstorm mode to explore a feature or enhancement idea. Stays in discussion mode only — no planning, no implementation. Use /agtx:sweep when ready to push outcomes to the board.
agtx-review
Self-review completed work. Check for correctness, edge cases, and code quality. Write review to .agtx/review.md and stop.