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 skills/justrach/codegraff2/test-reasoningnpx skills add justrach/codegraff2 --skill test-reasoninggit clone --depth 1 https://github.com/justrach/codegraff2What 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 | $0.00064 | $0.01030 |
| Opus 5 | $0.00032 | $0.00515 |
| Sonnet 5 | $0.00013 | $0.00206 |
| Haiku 4.5 | $0.00006 | $0.00103 |
Grade A, and why
test-reasoning 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.
This is a copy
100% identical to test-reasoning — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Reasoning Serialization
Validates that ReasoningConfig fields are correctly serialized into provider-specific JSON
for OpenRouter, Anthropic, GitHub Copilot, and Codex.
Quick Start
Run all tests with the bundled script:
./scripts/test-reasoning.sh
The script builds forge in debug mode, runs each provider/model combination, captures the
outgoing HTTP request body via FORGE_DEBUG_REQUESTS, and asserts the correct JSON fields.
Running a Single Test Manually
FORGE_DEBUG_REQUESTS="forge.request.json" \
FORGE_SESSION__PROVIDER_ID=<provider_id> \
FORGE_SESSION__MODEL_ID=<model_id> \
FORGE_REASONING__EFFORT=<effort> \
target/debug/forge -p "Hello!"
Then inspect .forge/forge.request.json for the expected fields.
Test Coverage
| Provider | Model | Config fields | Expected JSON field |
|---|---|---|---|
open_router |
openai/o4-mini |
effort: none|minimal|low|medium|high|xhigh |
reasoning.effort |
open_router |
openai/o4-mini |
max_tokens: 4000 |
reasoning.max_tokens |
open_router |
openai/o4-mini |
effort: high + exclude: true |
reasoning.effort + .exclude |
open_router |
openai/o4-mini |
enabled: true |
reasoning.enabled |
open_router |
anthropic/claude-opus-4-5 |
max_tokens: 4000 |
reasoning.max_tokens |
open_router |
moonshotai/kimi-k2 |
max_tokens: 4000 |
reasoning.max_tokens |
open_router |
moonshotai/kimi-k2 |
effort: high |
reasoning.effort |
open_router |
minimax/minimax-m2 |
max_tokens: 4000 |
reasoning.max_tokens |
open_router |
minimax/minimax-m2 |
effort: high |
reasoning.effort |
anthropic |
claude-opus-4-6 |
effort: low|medium|high|max |
output_config.effort |
anthropic |
claude-3-7-sonnet-20250219 |
enabled: true + max_tokens: 8000 |
thinking.type + budget_tokens |
github_copilot |
o4-mini |
effort: none|minimal|low|medium|high|xhigh |
reasoning_effort (top-level) |
codex |
gpt-5.1-codex |
effort: none|minimal|low|medium|high|xhigh |
reasoning.effort + .summary |
codex |
gpt-5.1-codex |
effort: medium + exclude: true |
reasoning.summary = "concise" |
| all providers | one model each | effort: invalid |
non-zero exit, no request written |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 62 lines · 64 tokens per session scan A 4f98815ab665
test-reasoning is a skill published in the GitHub repository justrach/codegraff2 (24 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 64 tokens to every session and 1,030 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to test-reasoning, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…