agentsclimarketplace
Sign in

Agent tester

Skill aAAaqwq/AGI-Super-Team/skills/agent-tester

Test agent: dry-run, unit, integration, compatibilityFrom its SKILL.md

Install
npx -y skills add aAAaqwq/AGI-Super-Team --skill agent-tester

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

3.2 KB, 828 tokens by cl100k_base, as published. Nobody here has run it

Agent Tester

Tests a built agent: dry-run, unit tests, integration, compatibility with other agents.

When to use

  • After Agent Builder has finished
  • "test agent X"
  • "check agent compatibility"

Input

  • Agent from $AGENTS_PATH/[name]/
  • Spec from $AGENTS_PATH/specs/[name].spec.md

How to execute

Step 1: Static analysis

Check the agent code:

  • File exists and runs without syntax errors
  • All imports resolve
  • Config file is valid
  • Paths in config exist
  • Credentials are accessible
  • Dry-run mode is implemented

Step 2: Dry-run test

Run the agent with --dry-run:

python3 $AGENTS_PATH/[name]/[name]_agent.py --dry-run

Check:

  • Agent starts without errors
  • Logs are clear
  • Shows what it WOULD do (without real side effects)
  • Execution time is reasonable

Step 3: Unit tests

Run tests:

python3 -m pytest $AGENTS_PATH/[name]/test_[name].py -v

Minimum tests:

  • Input parsing works
  • Business logic is correct on test data
  • Error handling works (bad input, missing files, API timeout)
  • Output format is correct

Step 4: Integration test (one run on real data)

WARNING: only with human approval!

  1. Back up data that the agent modifies:
cp [target.csv] [target.csv.backup]

  1. Run the agent once on real data

  2. Check output:

    • Data was written correctly
    • Format matches schema.yaml
    • Nothing broke
    • Git commit was created (if needed)

  3. If something is wrong -- rollback:

cp [target.csv.backup] [target.csv]

Step 5: Compatibility test

Check that the new agent does not conflict with existing ones:

## Compatibility Matrix

| Agent | Shared Files | Potential Conflict | Status |
|-------|-------------|-------------------|--------|
| Email Pipeline | activities.csv | Write conflict | ? |
| [other agents] | ... | ... | ? |

Specific checks:

  • File locks: can two agents write to the same CSV simultaneously
  • Data consistency: does the agent overwrite another agent's data
  • ID generation: do IDs conflict (person_id, activity_id, etc.)
  • Schedule overlap: do agents run at the same time
  • Git conflicts: does auto-commit create merge conflicts

Step 6: Report

Create a test report file:

$AGENTS_PATH/specs/[name].test-report.md

Report structure:

# Test Report: [Agent Name]

## Date: YYYY-MM-DD
## Tester: Process Analyst Agent

## Results

| Test | Status | Notes |
|------|--------|-------|
| Static analysis | PASS/FAIL | |
| Dry-run | PASS/FAIL | |
| Unit tests | PASS/FAIL | X/Y passed |
| Integration | PASS/FAIL | |
| Compatibility | PASS/FAIL | |

## Issues Found
1. [Issue description + severity]

## Recommendation
- [ ] READY for production
- [ ] NEEDS FIXES (list what)
- [ ] BLOCKED (list why)

Output

  • Test report in $AGENTS_PATH/specs/[name].test-report.md
  • PASS/FAIL verdict
  • List of issues if any

Related skills

  • process-analyst — creates the spec
  • agent-builder — builds the agent
  • change-review — validates CRM/PM changes

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most context ai engineering skills give in 828 tokens

Counted across 1,328 of the 2,349 authors here whose files we hold, read 2026-09-06

  • Dispatch a fresh subagent for each taskin 76 of 1328, across 59 files
  • Perform spec compliance review before code quality reviewin 44 of 1328, across 34 files
  • Dispatch a final code reviewer after all tasksin 38 of 1328, across 26 files
  • Answer subagent questions before allowing implementationin 36 of 1328, across 26 files
  • Use the least powerful model capable of the taskin 33 of 1328, across 26 files
  • Create a TodoWrite list for all tasksin 32 of 1328, across 22 files
  • Perform a task review after each implementationin 31 of 1328, across 24 files
  • Extract all tasks and context from the planin 29 of 1328, across 20 files
  • Provide full task text to subagentsin 28 of 1328, across 20 files
  • Use git worktrees for isolated workspacesin 25 of 1328, across 20 files
  • Specify the model explicitly when dispatching a subagentin 23 of 1328, across 18 files
  • Execute all tasks from the plan without stoppingin 21 of 1328, across 16 files

Said here and by no other author read

  • Run agent with dry-run flag
  • Execute unit tests using pytest
  • Backup data before integration testing
  • Run integration test only with human approval
  • Check for compatibility with existing agents
  • Create a test report file

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.