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/sd0xdev/sd0x-harness/test-deepnpx skills add sd0xdev/sd0x-harness --skill test-deepgit clone --depth 1 https://github.com/sd0xdev/sd0x-harnessWrote 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/sd0xdev/sd0x-harness/test-deep)<a href="https://agentmods.dev/skills/sd0xdev/sd0x-harness/test-deep"><img src="https://agentmods.dev/badge/skills/sd0xdev/sd0x-harness/test-deep.svg" alt="Measured on agentmods" 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 | $0.00077 | $0.02252 |
| Opus 5 | $0.00039 | $0.01126 |
| Sonnet 5 | $0.00015 | $0.00450 |
| Haiku 4.5 | $0.00008 | $0.00225 |
Grade A, and why
test-deep 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 3d 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Deep — Context-Aware Test Orchestration
Supplementary Agent
When test failures occur, dispatch background triage:
Agent({
description: "Analyze test failure root cause and suggest fixes",
subagent_type: "verify-app",
prompt: Analyze the following test failure: <failure output> Identify root cause and suggest minimal fix.
})
Trigger
- Keywords: context-aware testing, smart test, test orchestration, test triage, test failure analysis, test deep, run relevant tests
When NOT to Use
| Scenario | Alternative |
|---|---|
| Writing new tests | /post-dev-test |
| Reviewing test coverage | /codex-test-review |
| Generating unit tests | /codex-test-gen |
| Full manual test run | /verify |
| Code review | /codex-review-fast |
Prohibited Actions
❌ git add | git commit | git push — per @rules/git-workflow.md
This skill runs tests and may apply safe fixers, but does not commit. To commit, the user must invoke /smart-commit --execute separately.
Workflow
flowchart TD
U[User: /test-deep] --> S[Phase 0: Test Selection]
S --> |git diff mapping| T[Test Targets]
S --> |no mapping| F1[Framework --changedSince]
S --> |low confidence| F2[Full Suite]
T --> L[Phase 1: Progressive Ladder]
F1 --> L
F2 --> L
L --> |unit| R1[Run Unit Tests]
R1 --> |pass| R2[Run Integration Tests]
R1 --> |fail| TR[Phase 2: Triage Pipeline]
R2 --> |pass| R3[Run E2E Tests]
R2 --> |fail| TR
R3 --> |pass| DONE[All Pass]
R3 --> |fail| TR
TR --> P[Parser: Structured Tags]
P --> LLM[LLM: Root Cause + Action]
LLM --> FC[Phase 3: Fixer Catalog Lookup]
FC --> SG{Safety Gate}
SG --> |safe| AUTO[Auto-run Fix]
SG --> |side-effect| ASK[AskUserQuestion]
SG --> |destructive| BLOCK[Manual Only]
AUTO --> L
ASK --> |approved| L
Phase 0: Test Selection
Map code changes to test targets. See references/test-selection.md for full strategy.
Strategy priority:
What ships with it
3 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.
- 3d ago First seen · 246 lines · 77 tokens per session scan A e17a79ace932
test-deep is a skill published in the GitHub repository sd0xdev/sd0x-harness (188 stars, last pushed yesterday), licensed MIT. It adds 77 tokens to every session and 2,252 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
building
Implementation skill for writing production code with TDD. Covers the RED-GREEN-REFACTOR cycle, false-RED detection, vertical slicing, scope escalation, test process discipline, and code generation patterns. Loaded by component-builder and bug-investigator.
evaluator-write-qa
Internal Auto-Harness evaluator skill for sprint QA and QA report writing. Use only inside the Evaluator subagent during qa mode.
evaluator-write-final-parallel
Internal Auto-Harness evaluator skill for parallel final QA report aggregation. Use only inside the Evaluator subagent during evaluatorfinalparallel.
evaluator-write-qa-parallel
Internal Auto-Harness evaluator skill for parallel sprint QA and QA report writing. Use only inside the Evaluator subagent during evaluatorqaparallel.
evaluator-write-retest-parallel
Internal Auto-Harness evaluator skill for parallel sprint retest and retest report writing. Use only inside the Evaluator subagent during evaluatorretestparallel.
evaluator-write-retest
Internal Auto-Harness evaluator skill for sprint retest and retest report writing. Use only inside the Evaluator subagent during retest mode.