PiDeck Usage Probe Helper
ayuayue/PiDeck
Helps show a model provider's usage, balance or quota in PiDeck: checks built-in support, points to the dialog templates, or writes a custom probe entry.
Checks that ReasoningConfig fields are serialized into the right provider-specific JSON for OpenRouter, Anthropic, GitHub Copilot and Codex requests.
Install Reasoning Serialization Tests
$ npx skills add tailcallhq/forgecode --skill test-reasoning -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install tailcallhq/forgecode test-reasoning --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/tailcallhq/forgecode.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.forge/skills/test-reasoning .claude/skills/test-reasoning && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "test-reasoning" agent skill from https://github.com/tailcallhq/forgecode/tree/main/.forge/skills/test-reasoning into .claude/skills/test-reasoning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-reasoning", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/tailcallhq/forgecode/tree/main/.forge/skills/test-reasoningType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add tailcallhq/forgecode --skill test-reasoning -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install tailcallhq/forgecode test-reasoning --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tailcallhq/forgecode.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.forge/skills/test-reasoning .agents/skills/test-reasoning && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "test-reasoning" agent skill from https://github.com/tailcallhq/forgecode/tree/main/.forge/skills/test-reasoning into .agents/skills/test-reasoning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-reasoning", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add tailcallhq/forgecode --skill test-reasoning -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install tailcallhq/forgecode test-reasoning --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tailcallhq/forgecode.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.forge/skills/test-reasoning .cursor/skills/test-reasoning && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "test-reasoning" agent skill from https://github.com/tailcallhq/forgecode/tree/main/.forge/skills/test-reasoning into .cursor/skills/test-reasoning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-reasoning", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/tailcallhq/forgecode.git --path .forge/skills/test-reasoning--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add tailcallhq/forgecode --skill test-reasoning -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install tailcallhq/forgecode test-reasoning --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tailcallhq/forgecode.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.forge/skills/test-reasoning .gemini/skills/test-reasoning && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "test-reasoning" agent skill from https://github.com/tailcallhq/forgecode/tree/main/.forge/skills/test-reasoning into .gemini/skills/test-reasoning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-reasoning", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install tailcallhq/forgecode test-reasoningInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add tailcallhq/forgecode --skill test-reasoning -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/tailcallhq/forgecode.git skills-src && mkdir -p .github/skills && cp -r skills-src/.forge/skills/test-reasoning .github/skills/test-reasoning && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "test-reasoning" agent skill from https://github.com/tailcallhq/forgecode/tree/main/.forge/skills/test-reasoning into .github/skills/test-reasoning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-reasoning", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add tailcallhq/forgecode --skill test-reasoning -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install tailcallhq/forgecode test-reasoning --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tailcallhq/forgecode.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.forge/skills/test-reasoning .opencode/skills/test-reasoning && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "test-reasoning" agent skill from https://github.com/tailcallhq/forgecode/tree/main/.forge/skills/test-reasoning into .opencode/skills/test-reasoning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-reasoning", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
test-reasoning- GitHub stars
- 7.6k
- Token cost
- ~1k tokens
- SKILL.md length
- 207 words
- Files
- 2 (incl. scripts)
- Skills in repo
- 14
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Checks that ReasoningConfig fields are serialized into the right provider-specific JSON for OpenRouter, Anthropic, GitHub Copilot and Codex requests.
- Verifying that reasoning settings reach the provider request correctly
- SKILL.md covers Quick Start, Running a Single Test Manually, Test Coverage and References
- Runs Shell scripts from its folder
- After changing ReasoningConfig or a provider adapter
What it does
The bundled script scripts/test-reasoning.sh builds forge in debug mode, runs each provider and model combination, captures the outgoing HTTP request body through the FORGE_DEBUG_REQUESTS variable, and asserts that the expected JSON fields are present. To test one case by hand, you set that variable plus the provider and model IDs, run forge, and inspect .forge/forge.request.json.
A coverage table maps config fields to the JSON they should produce. For OpenRouter across several models, effort should appear as reasoning.effort, max_tokens as reasoning.max_tokens, enabled as reasoning.enabled, and exclude beside effort. For Anthropic, effort maps to output_config.effort. The table continues beyond what the excerpt shows.
When your agent uses it
- Verifying that reasoning settings reach the provider request correctly
- After changing ReasoningConfig or a provider adapter
- Checking the reasoning JSON fields for a newly added model
- Debugging a reasoning effort setting that seems to be ignored
Example prompts
- “Run the reasoning serialization tests and report which providers fail.”
- “Check that effort high on OpenRouter becomes reasoning.effort in the request body.”
- “Test the Anthropic provider's effort mapping with FORGE_DEBUG_REQUESTS.”
Requirements
- A forgecode checkout that builds in debug mode
What it can do on your machine
Read from SKILL.md and the folder at commit e11b93e. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Shell), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
developers.openai.complatform.claude.comopenrouter.ai
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Reasoning Serialization Tests loads about 1k tokens when it runs. Until then it costs about 82 tokens; SKILL.md has 207 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from tailcallhq/forgecode at commit e11b93e, republished under its Apache-2.0 licence (© tailcallhq). 207 words, ~1,037 tokens.
Download SKILL.mdSave it as
.claude/skills/test-reasoning/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- test-reasoning
- description
- Validate that reasoning parameters are correctly serialized and sent to provider APIs. Use when the user asks to test reasoning serialization, run reasoning tests, verify reasoning config fields, or check that ReasoningConfig maps correctly to provider-specific JSON (OpenRouter, Anthropic, GitHub Copilot, Codex).
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.shThe 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 |
Tests for unconfigured providers are skipped automatically. Invalid-effort tests run regardless of credentials — the rejection happens at config parse time before any provider interaction.
References
© tailcallhq, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file (scripts) in .forge/skills/test-reasoning of tailcallhq/forgecode.
- SKILL.md
- scripts/test-reasoning.sh
Open the folder on GitHubat commit e11b93e
Compare with similar skills
Reasoning Serialization Tests next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Reasoning Serialization Tests this skilltailcallhq/forgecode | 7.6k | — | ~1k | Automated safety check: Pass | Apache-2.0 | |
| PiDeck Usage Probe Helperayuayue/PiDeck | 1k | — | ~1.4k | Automated safety check: Pass | MIT | |
| LLM Modelsmajiayu000/claude-skill-registry | 666 | 1 repos | ~992 | Automated safety check: Pass | MIT | |
| Proxy Mode ReferenceMadAppGang/claude-code | 284 | — | ~1.3k | Automated safety check: Pass | MIT | |
| Using Ccproxy Inspectorstarbaser/ccproxy | 350 | — | ~2.7k | Automated safety check: Pass | Custom licence | |
| Using Ccproxy APIstarbaser/ccproxy | 350 | — | ~4k | Automated safety check: Pass | Custom licence |
Similar skills
LLM Models
majiayu000/claude-skill-registry
Access Claude, Gemini, Kimi, GLM and 100+ LLMs via inference.sh CLI using OpenRouter.
Proxy Mode Reference
MadAppGang/claude-code
Reference guide for using external AI models via claudish CLI.
Using Ccproxy Inspector
starbaser/ccproxy
Operates the ccproxy inspector MITM system for intercepting, inspecting, and transforming LLM API traffic.
Using Ccproxy API
starbaser/ccproxy
Guides users through ccproxy as an OpenAI-compatible and Anthropic-compatible LLM API server with SDK integration, OAuth authentication, sentinel key substitution, model routing, and troubleshooting.
Keirouter Chat
mydisha/keirouter
Chat / code generation via KeiRouter using OpenAI /v1/chat/completions or Anthropic /v1/messages format with streaming + auto-fallback combos.
More from tailcallhq/forgecode
All 14 skills in this repoGit Merge Conflict Resolver
tailcallhq/forgecode
Resolves Git merge conflicts with a plan-first workflow that keeps both sides' intent, regenerates lock files and backs up deleted-but-modified files.
Forge CLI Debug Workflow
tailcallhq/forgecode
Gives a systematic process for debugging the forge CLI: build in debug mode, check the latest help output, test with the non-interactive -p flag, and clone conversations before reproducing bugs.
FIXME Resolver
tailcallhq/forgecode
Finds every FIXME comment in a codebase, groups related ones across files into one task, implements the work they describe and removes the comments once it is done.
Implementation Plan Creator
tailcallhq/forgecode
Writes a structured Markdown implementation plan with checkbox tasks, verification criteria and risks, then checks it with a validation script; no code changes.
Release Notes Writer
tailcallhq/forgecode
Pulls a GitHub release and every linked pull request, then writes polished, factual release notes from the combined set of changes.
Skill Creation Guide
tailcallhq/forgecode
Guidance for creating and updating agent skills: what skills provide, keeping context lean, choosing how specific to be, and how SKILL.md and bundled resources are laid out.
Related
Works with
Categories
Questions about Reasoning Serialization Tests
What does Reasoning Serialization Tests do?
Checks that ReasoningConfig fields are serialized into the right provider-specific JSON for OpenRouter, Anthropic, GitHub Copilot and Codex requests. sh builds forge in debug mode, runs each provider and model combination, captures the outgoing HTTP request body through the FORGE_DEBUG_REQUESTS variable, and asserts that the expected JSON fields are present.json.
When should I use Reasoning Serialization Tests?
Reasoning Serialization Tests fits situations like: verifying that reasoning settings reach the provider request correctly; after changing ReasoningConfig or a provider adapter; checking the reasoning JSON fields for a newly added model; debugging a reasoning effort setting that seems to be ignored.
How do I install Reasoning Serialization Tests in Claude Code?
Run `npx skills add tailcallhq/forgecode --skill test-reasoning -a claude-code`. Or copy the skill folder (.forge/skills/test-reasoning in tailcallhq/forgecode) into .claude/skills/test-reasoning in your project. Claude Code loads it when a task matches its description.
How do I install Reasoning Serialization Tests in Codex?
Run `npx skills add tailcallhq/forgecode --skill test-reasoning -a codex`. Or copy the skill folder (.forge/skills/test-reasoning in tailcallhq/forgecode) into .agents/skills/test-reasoning in your project. Codex loads it when a task matches its description.
Can I use Reasoning Serialization Tests in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add tailcallhq/forgecode --skill test-reasoning -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/test-reasoning, .gemini/skills/test-reasoning, .github/skills/test-reasoning and .opencode/skills/test-reasoning in your project.
What does Reasoning Serialization Tests need to run?
Going by SKILL.md and its folder, Reasoning Serialization Tests needs a shell for the scripts in its folder. Our summary lists: A forgecode checkout that builds in debug mode.
Does Reasoning Serialization Tests access the network?
SKILL.md names 3 domains. As links in the text: developers.openai.com, platform.claude.com and openrouter.ai. This is read from the text; nothing was executed.
Is Reasoning Serialization Tests safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Reasoning Serialization Tests use?
Reasoning Serialization Tests is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Reasoning Serialization Tests use?
About 1k tokens (SKILL.md is roughly 4.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Reasoning Serialization Tests?
Skills that share tags, products or a category with Reasoning Serialization Tests: PiDeck Usage Probe Helper (ayuayue/PiDeck, 1k stars), LLM Models (majiayu000/claude-skill-registry, 666 stars), Proxy Mode Reference (MadAppGang/claude-code, 284 stars) and Using Ccproxy Inspector (starbaser/ccproxy, 350 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Reasoning Serialization Tests?
tailcallhq (a GitHub organization) maintains it in tailcallhq/forgecode, which has 7,641 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 8, 2026.
Source: tailcallhq/forgecode on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.