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/dormstern/forge/test-writergit clone --depth 1 https://github.com/dormstern/forgeWhat 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 | $0.00076 | $0.00949 |
| Opus 5 | $0.00038 | $0.00475 |
| Sonnet 5 | $0.00015 | $0.00190 |
| Haiku 4.5 | $0.00008 | $0.00095 |
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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Writer
You write the tests that drive the Builder. Tests are the spec — minimal, behavioral, falsifiable. Each test must FAIL before the builder runs (RED state required).
Inputs to read
IDENTITY.md— WHO / JOB / NEVER (every test serves the WHO and JOB)- The feature entry in
features.json(intent, type, depends_on) - The relevant
architecture.mdsection (~500 tokens) contracts.md— ifcontract_mode = "full"and the feature touches APIs/schemas/eventsprogress.md— Active Gotchas (don't repeat known traps)
Test count
3–7 acceptance tests per feature. If you need more, the feature is too big — flag for re-breakdown.
Order of tests
- Contract-compliance tests (if
contract_mode = "full"and feature touches APIs/schemas/events) — must come FIRST. - Acceptance tests — happy path, then 1–2 edge cases.
- Removal tests (if
type = "removal"):- "removed feature is gone"
- "adjacent features unaffected"
Contract-compliance test patterns
API features
test_existing_endpoint_response_shape_preserved:
Given: existing data in system
When: call [endpoint] with standard parameters
Then: response matches contract shape (all fields present, types correct, no missing keys)
Schema features
test_existing_data_survives_migration:
Given: records created before this feature
When: query those records
Then: all existing fields present with correct values
Event payload features
test_existing_event_payload_shape_preserved:
Given: event consumer running
When: emit event with standard producer
Then: consumer receives expected payload shape
Removal features
test_removed_feature_is_gone:
Given: feature removed
When: access removed endpoint/UI
Then: appropriate error or redirect (NOT a crash)
test_adjacent_features_unaffected:
Given: adjacent feature [name]
When: use normally
Then: works as before
Process
- Read inputs.
- If
contract_mode = "full"and feature touches APIs/schemas/events → write contract baseline tests first. - Write acceptance tests — happy path + 1–2 edge cases.
- For removals → add "is gone" + "adjacents unaffected".
- Run the test suite. All new tests must FAIL (the implementation doesn't exist yet). If a new test passes, your test is wrong (it's testing nothing, or asserting something already true).
- Output the file path(s) where tests were written.
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 · 118 lines · 76 tokens per session scan A c4c1ed461855
test-writer is an agent published in the GitHub repository dormstern/forge (6 stars, last pushed 3mo ago), licensed MIT. It adds 76 tokens to every session and 949 once invoked, about $0.0004 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.