tracepilot-gemini-cli: Skill for Gemini CLI

.gemini/skills/behavioral-evals/SKILL.md

behavioral-evals is a skill for Gemini CLI from priyanshuchawda/tracepilot-gemini-cli. It costs 39 tokens per session (616 once invoked), scanned A, a copy of behavioral-evals, Apache-2.0.

A guide for creating and running behavioral evaluations, which test an agent's decisions and tool choices rather than only checking whether code runs. It also covers fixing failures and promoting tests into regression checks.

In plain words
What is it for?
Use it to build evaluations for prompts, tools, and agent workflows, select the appropriate test harness, seed realistic files, and lock reliable tests against regressions.
Why use it?
It helps detect changes that make an agent choose the wrong action or behave differently, problems that ordinary software tests may miss.

Skill for Gemini CLI

Written for Gemini CLI: installed under .gemini/. Also seen: mentions Gemini CLI.

This is priyanshuchawda/tracepilot-gemini-cli's own configuration. It tells Gemini CLI how to work on tracepilot-gemini-cli itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything tracepilot-gemini-cli configures →

Reuse

Borrowing it

Nothing to install: this file belongs to priyanshuchawda/tracepilot-gemini-cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/priyanshuchawda/tracepilot-gemini-cli/main/.gemini/skills/behavioral-evals/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/priyanshuchawda/tracepilot-gemini-cli

Made for: Gemini CLI.

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.

agentmods badge for behavioral-evals

README.md
[![agentmods](https://agentmods.dev/badge/skills/priyanshuchawda/tracepilot-gemini-cli/behavioral-evals/github.svg)](https://agentmods.dev/skills/priyanshuchawda/tracepilot-gemini-cli/behavioral-evals)
Your own site
<a href="https://agentmods.dev/skills/priyanshuchawda/tracepilot-gemini-cli/behavioral-evals"><img src="https://agentmods.dev/badge/skills/priyanshuchawda/tracepilot-gemini-cli/behavioral-evals/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.

agentmods 80×15 button for behavioral-evals

Your own site · 80×15
<a href="https://agentmods.dev/skills/priyanshuchawda/tracepilot-gemini-cli/behavioral-evals"><img src="https://agentmods.dev/badge/skills/priyanshuchawda/tracepilot-gemini-cli/behavioral-evals.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 616 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 100% copy Near-identical to another mod 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00039 $0.00616
Opus 5 $0.00019 $0.00308
Sonnet 5 $0.00008 $0.00123
Haiku 4.5 $0.00004 $0.00062

Measured 9d ago against content hash c1ab849bb3b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

behavioral-evals 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 9d 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.

Origin

This is a copy

100% identical to behavioral-evals — 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.

.gemini/skills/behavioral-evals/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Behavioral Evals

Overview

Behavioral evaluations (evals) are tests that validate the agent's decision-making (e.g., tool choice) rather than pure functionality. They are critical for verifying prompt changes, debugging steerability, and preventing regressions.

[!NOTE] Single Source of Truth: For core concepts, policies, running tests, and general best practices, always refer to evals/README.md.


🔄 Workflow Decision Tree

  1. Does a prompt/tool change need validation?
    • No -> Normal integration tests.
    • Yes -> Continue below.
  2. Is it UI/Interaction heavy?
  3. Is it a new test?
    • Yes -> Set policy to USUALLY_PASSES.
    • No -> ALWAYS_PASSES (locks in regression).
  4. Are you fixing a failure or promoting a test?

📋 Quick Checklist

1. Setup Workspace

Seed the workspace with necessary files using the files object to simulate a realistic scenario (e.g., NodeJS project with package.json).

2. Write Assertions

Audit agent decisions using rig.setBreakpoint() (AppRig only) or index verification on rig.readToolLogs().

3. Verify

Run single tests locally with Vitest. Confirm stability locally before relying on CI workflows.


📦 Bundled Resources

Detailed procedural guides:

  • creating.md: Assertion strategies, Rig selection, Mock MCPs.
  • fixing.md: Step-by-step automated investigation, architecture diagnosis guidelines.
  • promoting.md: Candidate identification criteria and threshold guidelines.

Read the full file on GitHub · 57 lines

Files

What ships with it

6 files 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.

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.

  1. 9d ago First seen · 57 lines · 39 tokens per session scan A c1ab849bb3b1

Subscribe to this mod's changes

behavioral-evals is a skill published in the GitHub repository priyanshuchawda/tracepilot-gemini-cli (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 39 tokens to every session and 616 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to behavioral-evals, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

superpowers

Always-on. The main development method: Plan → TDD → Implement → Verify → Report. Use for ANY non-trivial task. Do not write code without a plan and a test. Complex tasks (>3 files) → split into atomic tasks. Bug fix → Prove-It Pattern (reproduce with a test before the fix).

oleg494/coding-kit · 70 tokens

test-driven-development

Drives development with tests. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.

oleg494/coding-kit · 50 tokens

testing-discipline

Use when the user wants to: add/fix tests, understand what is covered, determine whether something is "done", reproduce a bug with a test, check limits/rate-limit/failures, or when tests are written against a real DB/network. Covers: isolation from the prod store, domain-first tests, test names as a spec, boundary…

oleg494/coding-kit · 110 tokens

agentic-evals

Design evaluation contracts and test plans for agentic systems. Create deterministic tests, trajectory evals, quality dimensions, gold-set criteria, and CI gates before or after implementation. Use when asked for tests first, an eval plan, success criteria, non-deterministic testing, LLM-as-judge setup, or…

browoz/agentic-sdlc-skills · 95 tokens

fable-judge

Adversarial verification of finished work: re-runs the claimed verifications, diffs what changed, detects false "done" claims, delivers an evidence-based verdict (VERIFIED / VERIFIED WITH CAVEATS / REFUTED). Use after any agent or model claims work is complete — "/fable-judge", "judge this work", "verify what it did".…

oleg494/coding-kit · 98 tokens

verification-before-completion

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always.

oleg494/coding-kit · 43 tokens