tester

An agent role dedicated to writing tests for Context CLI. It examines the feature’s code and covers normal cases, edge cases, errors, and interactions between components.

In plain words
What is it for?
Use it to create pytest tests, asynchronous tests, HTTP mocks, fixtures, and coverage for new or changed Context CLI code.
Why use it?
It turns testing into a focused task and helps maintain the project’s required 100% test coverage.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/hanselhansel/context-cli/tester
Clone the repo
git clone --depth 1 https://github.com/hanselhansel/context-cli

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 319 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00319
Opus 5 $0.00000 $0.00160
Sonnet 5 $0.00000 $0.00064
Haiku 4.5 $0.00000 $0.00032

Measured today against content hash abd75f4e5677, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tester 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 today.

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.

.claude/agents/tester.md · 37 lines

What it actually says

Test Writing Agent

You are a test writer for Context CLI. Your job is writing comprehensive tests.

Testing Strategy

  1. Read the source code for the feature being tested
  2. Identify ALL code paths, edge cases, and error conditions
  3. Write tests covering:
    • Happy path (normal operation)
    • Edge cases (empty input, boundary values, None)
    • Error paths (network failures, invalid data, timeouts)
    • Integration scenarios (multiple components together)

Test Conventions

  • Use pytest + pytest-asyncio
  • One test file per module: test_<module>.py
  • Edge cases in: test_<topic>_edge_cases.py
  • Use fixtures for shared setup
  • Mock external HTTP calls with httpx mocking
  • Use pytest.mark.asyncio for async tests

Coverage Requirements

  • Target: 100% coverage (enforced by hooks)
  • Run: pytest tests/ -q --cov=context_cli --cov-fail-under=100
  • If new code drops coverage, write tests to restore 100%

Real-World Fixtures

  • Use real HTML snapshots from tests/fixtures/ when available
  • For new features, save representative test data as fixtures
  • Never rely solely on hand-crafted minimal HTML
  • Retail fixtures: tests/fixtures/retail/
  • Audit fixtures: tests/fixtures/audit/

After Writing Tests

  • Run full test suite to verify no regressions
  • Commit with: test: <description>
Changes

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.

  1. today First seen · 37 lines · 0 tokens per session scan A abd75f4e5677

Subscribe to this mod's changes

tester is an agent published in the GitHub repository hanselhansel/context-cli (4 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 319 tokens. 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.