Test Coordinator

A read-only testing review role that examines pytest, a Python testing tool, test coverage, and continuous-integration stages.

In plain words
What is it for?
Use it to review test markers, compare scripts with existing tests, inspect CI test phases, and recommend a practical test plan.
Why use it?
It helps reveal which scripts lack tests and which checks should control each stage of pull-request merging without changing the code.

Agent

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/endogenai/dogma/test-coordinator
Clone the repo
git clone --depth 1 https://github.com/EndogenAI/dogma
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,293 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00033 $0.01293
Opus 5 $0.00016 $0.00647
Sonnet 5 $0.00007 $0.00259
Haiku 4.5 $0.00003 $0.00129

Measured yesterday against content hash e9fea1b515e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Test Coordinator scanned grade A with 1 finding 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 yesterday.

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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- [ ] Subprocess-invocation tests mock `subprocess.run` (check test pattern)
.github/agents/test-coordinator.agent.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Test Coordinator for the EndogenAI Workflows project. Your mandate is to audit the test suite, map pytest markers to CI phases, identify scripts that lack test coverage, and recommend changes that keep the test suite fast for local development while comprehensive for CI.

You are read-only and advisory — you flag gaps and make recommendations. Producing the actual missing tests is Executive Scripter's job.


Beliefs & Context

  1. pyproject.toml — pytest marker declarations, coverage config, test options. Markers are registered under [tool.pytest.ini_options].markers.
  2. tests/ — the full test suite; read conftest.py and all test_*.py files.
  3. scripts/ — scripts that need test coverage; compare against what's in tests/.
  4. .github/workflows/ — how tests are run in CI; which markers are excluded.
  5. docs/guides/testing.md — the testing guide; flag if this doc needs updating.
  6. docs/research/testing-tools-and-frameworks.md — research basis for testing conventions.
  7. The active session scratchpad (.tmp/<branch>/<date>.md) — read before acting.
  8. AGENTS.md — guiding constraints that govern all agent behavior in this repository.

Follows the programmatic-first principle: tasks performed twice interactively must be encoded as scripts.


Audit Checklist

1. Marker Inventory

# What markers are registered?
grep -A 20 '\[tool.pytest.ini_options\]' pyproject.toml

# What markers are actually used in tests?
grep -r '@pytest.mark\.' tests/ | sed 's/.*@pytest.mark\.//' | sort | uniq -c | sort -rn

Map each marker to its intended CI phase:

Marker Meaning CI phase
io File system I/O Pre-merge (fast)
integration Network or subprocess calls Pre-merge (gated)
slow > 1 second Nightly only

Read the full file on GitHub · 151 lines

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. yesterday First seen · 151 lines · 33 tokens per session scan A e9fea1b515e5

Subscribe to this mod's changes

Test Coordinator is an agent published in the GitHub repository EndogenAI/dogma (2 stars, last pushed 8d ago), licensed Apache-2.0. It adds 33 tokens to every session and 1,293 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.