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 AcKeskin/contexture --skill write-testsgit clone --depth 1 https://github.com/AcKeskin/contextureWrote 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/ackeskin/contexture/write-tests)<a href="https://agentmods.dev/skills/ackeskin/contexture/write-tests"><img src="https://agentmods.dev/badge/skills/ackeskin/contexture/write-tests/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/ackeskin/contexture/write-tests"><img src="https://agentmods.dev/badge/skills/ackeskin/contexture/write-tests.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 | $0.00057 | $0.02711 |
| Opus 5 | $0.00028 | $0.01355 |
| Sonnet 5 | $0.00011 | $0.00542 |
| Haiku 4.5 | $0.00006 | $0.00271 |
Grade A, and why
write-tests 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 5d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
write-tests
The test-authoring organ. Fills the hole between test-driven-development (the test-first workflow for new code) and the testability design rule (the code-side rule for making code testable): pointed at existing code, it authors a quality suite to a standard. It writes to universal/test-quality.md — the standard /review also audits against.
When to run
- User types
/write-tests <target>(or no arg → prompt for a target). - Natural language: "write tests for this", "add tests for
Invoice", "I need a test suite for the billing module". - Do not auto-fire. Mode A, user-invoked. Authoring tests is a deliberate act. No hook, no session trigger. (Distinct from
test-driven-development, which is the workflow you follow while writing new code — that one is invoked when you're about to build a feature; this one is pointed at code that already exists.)
Inputs
-
Target — a function, class, module, file, or directory. With no arg, prompt:
What should I write tests for? A function, class, file, or module.
-
Working directory —
$CLAUDE_PROJECT_DIRorcwd. Anchors framework detection, the extracted test-convention lookup, and where tests are written. -
Per-plan and per-flag confirmations — collected at the plan gate (§4) and on flagged-as-suspicious behaviors (§5). Collaborator principle — never author blind, never enshrine a suspected bug silently.
Procedure
1. Resolve the target
Resolve the target argument to concrete code: a file, a symbol within a file (grep for the declaration), a directory (each file), or a module. If ambiguous, list candidates and ask. If the target has no testable surface (a pure constant file, generated code), say so and stop rather than authoring vacuous tests.
2. Detect framework + conventions
Determine how this project tests, in this precedence:
- Extracted test conventions — if
<project>/.claude/rules/<lang>/conventions.mdexists and has a test-conventions section, use it. It is the project's own observed style; conform to it. - Existing tests — read the project's existing test files. Detect the framework (xUnit / NUnit / MSTest, Jest / vitest / mocha, pytest / unittest, cargo test, GoogleTest, …), the layout (where tests live, file naming), and the conventions (test naming pattern, fixture/setup style, assertion library).
- Inference + confirm — when neither is present, infer the most idiomatic framework + conventions for the language and surface them explicitly:
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.
- 5d ago First seen · 138 lines · 57 tokens per session scan A 4674a8ffce35
write-tests is a skill published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 2,711 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 2026-09-03.
Other skills, from other repositories
accessibility-a11y
WCAG 2.2 compliance, ARIA patterns, keyboard navigation, screen readers, automated testing.
verification-contract
Internal contract: one compact frozen ACCEPTANCE.md per delivery unit, its validation ladder, anti-weakening rules, and blob-bound execution receipt. Consumed by planners, execute-phase, and review-change.
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
V3 Security Overhaul
Complete security architecture overhaul for claude-flow v3. Addresses critical CVEs (CVE-1, CVE-2, CVE-3) and implements secure-by-default patterns. Use for security-first v3 implementation.
verify
Verify a code change does what it should by running the app.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.