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 SII-Holos/synergy --skill testing-guidegit clone --depth 1 https://github.com/SII-Holos/synergyWrote 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/sii-holos/synergy/testing-guide)<a href="https://agentmods.dev/skills/sii-holos/synergy/testing-guide"><img src="https://agentmods.dev/badge/skills/sii-holos/synergy/testing-guide/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/sii-holos/synergy/testing-guide"><img src="https://agentmods.dev/badge/skills/sii-holos/synergy/testing-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 11 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00060 | $0.01322 |
| Opus 5.5 | $0.00024 | $0.00529 |
| Sonnet 5.5 | $0.00012 | $0.00264 |
| Haiku 4.5 | $0.00006 | $0.00132 |
Grade A, and why
testing-guide 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.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Synergy Behavior
Development Feedback Loop
Start with bun run verify plan to inspect the working-tree impact, including uncommitted new files. Iterate with the narrow behavior test. Before publication, run bun run verify local --test <repository-relative-test> with every relevant test selected explicitly. The owning executor validates the selection, passes static gates, then runs selected tests with fresh coverage and checks new measurable source. Complete package coverage and platform matrices remain pending CI evidence.
Use bun run verify coverage --package <workspace> when changing coverage policy, removing substantial test coverage or changing instrumentation. A focused LCOV report cannot establish package thresholds. Finish generation and self-review before this checkpoint. Collect all causal failures from one CI attempt before making the next focused correction; infrastructure retries retain the same SHA.
Avoid concurrent artifact mutation
Finish or cancel concurrent file writers before final verification. Never run static gates alongside browser suites or builds in one worktree. Reuse passing evidence unless changed inputs invalidate it; preserve isolated Homes, fresh reports and real Scope fixtures. Raw Harness coverage/parallel commands are unsafe; use the canonical executor.
Read the domain guidance when this area is affected.
Workbench Presentation Acceptance
Read the domain guidance when this area is affected.
Local Joint Acceptance
Read the domain guidance when this area is affected.
Review Test Value and CI Cost
- Before adding a scenario, inspect nearby coverage and name the observable behavior, the real failure it prevents, and what existing tests leave uncovered. Extend a suitable existing test when it already owns that behavior. File size, assertion count and coverage percentage alone do not establish value.
- Review the affected old tests in the same change. Delete obsolete behavior, consolidate duplicate coverage, and replace assertions about source strings, callback names, incidental structure or fixed style values with observable results where needed. Record what was retained, combined or removed and why; there is no quota for adding or deleting tests.
- Put shared behavior at its lowest useful level. Keep adapter-specific integration at each adapter; add model, protocol, platform or outcome combinations only when they protect a distinct failure. Reuse immutable preparation while retaining separate mutable Homes, processes and DOMs.
- When replacing expensive acceptance, demonstrate that the retained test rejects a relevant fault such as a missing file edit, lost recording or failed continuation. Preserve public lifecycle, installation, migration, cancellation and recovery checks and coverage floors. Repetition and long sessions need an identified size, duration or accumulation failure; duplicate historical stress belongs in an explicit diagnostic.
- Measure preparation, execution, cleanup, upload and queues for changes to expensive fixtures, matrices or CI. Compare equivalent cold and warm runs, report the incremental cost and its useful coverage, and update task weights from observed time. Diagnose flakes at their observed stage; blanket retries, longer sleeps and hidden skips cannot justify growth. Use CI cost policy when reviewing a longer critical path.
What ships with it
5 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.
- 2d ago Changed 2fb9b5cf7046
- 4d ago Changed 0bd0448370df
- 8d ago Changed · +4 lines 2e8f9c5d2998
- 12d ago Changed · -350 lines 55628bc0c108
- 14d ago Changed · +12 lines bfc3b03a48bf
- 16d ago Changed · +2 lines c2be65109656
- 17d ago Changed · +12 lines bb081689d6ec
- 18d ago Changed · +18 lines ab92f0db7543
- 19d ago Changed · +9 lines bc83bc33f1aa
- 21d ago First seen · 368 lines · 60 tokens per session scan A cdc69d27e949
testing-guide is a skill published in the GitHub repository SII-Holos/synergy (388 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 1,322 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
conductor-implement
Execute tasks from a track's implementation plan following TDD workflow.
principle-test-behavior-not-implementation
Apply when you write, change, or keep a test. Assert what the code's users can observe, so that the test fails when that behavior breaks and keeps passing when only the internals change.
iterative-development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.
mobiai-mobile-tdd
You MUST use this before writing any implementation code for a mobile feature, bug fix, refactor, or behavior change. Tests come before implementation — no exceptions.
tdd
This skill should be used when the user wants to implement features or fix bugs using test-driven development. Enforces the RED-GREEN-REFACTOR cycle with vertical slicing, context isolation between test writing and implementation, human checkpoints, and auto-test feedback loops. Uses multi-agent orchestration with the…