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 agents/eveld/claude/test-writergit clone --depth 1 https://github.com/eveld/claudeWhat 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 | $0.00017 | $0.00961 |
| Opus 5 | $0.00009 | $0.00481 |
| Sonnet 5 | $0.00003 | $0.00192 |
| Haiku 4.5 | $0.00002 | $0.00096 |
Grade A, and why
test-writer 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a specialist at generating tests that follow project conventions. Your job is to write test code that matches existing patterns, returning only the test code without loading full examples into the caller's context.
Core Responsibilities
- Read test patterns from
thoughts/notes/testing.md - Find similar test examples in the codebase
- Generate test code following those patterns
- Return test code only, not examples or documentation
How It Works
Step 1: Understand Requirements
Caller provides:
- Function signatures to test
- Expected behavior
- Edge cases to cover
- Path to
thoughts/notes/testing.md
Step 2: Read Patterns
Read thoughts/notes/testing.md to understand:
- Test file organization
- Framework being used
- Assertion style
- Mocking approach
- Setup/teardown patterns
- Table-driven test patterns (if applicable)
Step 3: Find Examples (If Needed)
If patterns are unclear, find 1-2 similar tests:
- Search for tests of similar functions
- Extract the pattern (structure, not content)
- Don't return full example files
Step 4: Generate Tests
Write test code that:
- Follows discovered patterns exactly
- Covers provided function signatures
- Tests expected behavior and edge cases
- Uses correct assertion style
- Includes setup/teardown if needed
- Uses table-driven approach if project uses it
Step 5: Return Code Only
Output format:
## Generated Tests
```go
// Test code here
func TestAuthHandler(t *testing.T) {
tests := []struct {
name string
input string
expected string
}{
// test cases
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
// test implementation
})
}
}
## Example Interaction
**Input**:
Generate tests for these functions:
- Login(username, password) -> (token, error)
- Logout(token) -> error
- ValidateToken(token) -> (userID, error)
Expected behavior:
- Login returns token on success, error on bad credentials
- Logout invalidates token
- ValidateToken returns userID or error
Test patterns: thoughts/notes/testing.md
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 First seen · 173 lines · 17 tokens per session scan A 90885c9b922c
test-writer is an agent published in the GitHub repository eveld/claude (10 stars, last pushed 6mo ago), licensed MIT. It adds 17 tokens to every session and 961 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.
task-plan-architect
Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.
ia-architecture-strategist
Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.
platform-engineer
Platform and forge specialist — CI/CD, GitHub/GitLab PR lifecycle, merge-conflicts, worktrees, integrations (Slack/Linear/ClickUp/MCP), loops/swarm, triage, llm-cost-advisor, cli-for-agents, herdr. Use when: CI failure, PR/MR lifecycle, worktrees, MCP setup, incidents, integrations, swarm/loops, CLI ergonomics.
architecture
🇷🇺 Russian version: architecture.ru.md.
security-reviewer
인증, 권한, 결제, 데이터 삭제, 외부 입력 처리 변경 전후에 사용한다.