A tool that turns the rules in a skill.md file into a fixed Python decision tree and a test dataset. It can also review every skill in a directory and rank its findings.

Use it to convert a skill's decision logic into Python, challenge that logic with multiple reviewer personas, and export tests and the final tree.

It makes prompt-based decisions consistent, reviewable, and testable instead of relying on changing model responses.

temper — Command for Claude Code by CyrilLeMat/temper-skills

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.

Clone the repo

git clone --depth 1 https://github.com/CyrilLeMat/temper-skills

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/cyrillemat/temper-skills/temper/github.svg)](https://agentmods.dev/commands/cyrillemat/temper-skills/temper)

Your own site

<a href="https://agentmods.dev/commands/cyrillemat/temper-skills/temper"><img src="https://agentmods.dev/badge/commands/cyrillemat/temper-skills/temper/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/cyrillemat/temper-skills/temper"><img src="https://agentmods.dev/badge/commands/cyrillemat/temper-skills/temper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 184 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00028	$0.00184
Opus 5.5	$0.00011	$0.00074
Sonnet 5.5	$0.00006	$0.00037
Haiku 4.5	$0.00003	$0.00018

Measured 2mo ago against content hash 332f3b23e3b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

temper 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 2mo 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.

.claude/commands/temper.md · 15 lines

What it actually says

Use the temper-skills skill to compile the decision logic of $ARGUMENTS into a deterministic Python decision tree plus its adversarially-written validation dataset. If $ARGUMENTS is a directory, run the skill's library sweep instead: audit every skill in it and present the ranked findings table before tempering anything.

Run the adversarial loop on the Claude Code subscription using persona subagents: draft the tree, critique it each round with the five personas (in parallel), arbitrate and show the scored round panel, gate with the user, and converge when every persona scores ≥ 8 with no new gray zone. Then export the tree deterministically with python -m temper_skills.export_tree.

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.

2mo ago First seen · 15 lines · 28 tokens per session scan A 332f3b23e3b1

Subscribe to this mod's changes

temper is a command published in the GitHub repository CyrilLeMat/temper-skills (4 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 184 once invoked, about $0.0001 per session on Opus 5.5. 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.

Building agents Claude Code agent-skills claude claude-skills decision-tree determinism

temper next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
temperCyrilLeMat/temper-skills	Command	4	2mo ago	Apache-2.0	A	28	Claude Code
genshijin-compressInterfaceX-co-jp/genshijin	Command	332	27d ago	MIT	A	17	Claude Code
design-formAmey-Thakur/AI-SKILLS	Command	13	2mo ago	MIT	A	19	Claude Code
reviewnunoamorim99/agile-ledger	Command	1	15d ago	MIT	A	16	Claude Code
standupnunoamorim99/agile-ledger	Command	1	15d ago	MIT	A	9	Claude Code
enum-udppashki975/thm-claude-kit	Command	2	2mo ago	MIT	A	16	Claude Code
configure-chiliformsChili-Piper/mcp-assets	Command	8	2d ago	none	A	38	Claude Code