new-objective

new-objective is a skill for Claude Code, Codex from a16z/jolt. It costs 13 tokens per session (1,316 once invoked), scanned A, original, Apache-2.0.

A guided workflow for adding a new measurement objective to the Rust-based jolt-eval project. An objective is a defined score or benchmark, such as a code-complexity measure or a performance measurement.

In plain words
What is it for?
Use it when adding a static-analysis or performance objective to jolt-eval, including its registration, scoring function, benchmark, and target synchronisation.
Why use it?
It handles the repeated project wiring and enforces the distinction between analysing source code and measuring runtime performance. It also checks the name and requires linting and tests before success is reported.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/a16z/jolt/new-objective
Any agent
npx skills add a16z/jolt --skill new-objective
Clone the repo
git clone --depth 1 https://github.com/a16z/jolt

Made for: Claude Code, Codex.

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 new-objective

README.md
[![agentmods](https://agentmods.dev/badge/skills/a16z/jolt/new-objective.svg)](https://agentmods.dev/skills/a16z/jolt/new-objective)
Your own site
<a href="https://agentmods.dev/skills/a16z/jolt/new-objective"><img src="https://agentmods.dev/badge/skills/a16z/jolt/new-objective.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,316 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00013 $0.01316
Opus 5 $0.00006 $0.00658
Sonnet 5 $0.00003 $0.00263
Haiku 4.5 $0.00001 $0.00132

Measured 4d ago against content hash 376bf4ad8463, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

new-objective 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 4d 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/skills/new-objective/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This skill handles all the boilerplate: creating the objective struct, implementing the Objective trait, registering it in the appropriate enum, creating a const key, adding an ObjectiveFunction, creating a Criterion benchmark, and running sync_targets.sh.

<Execution_Policy>

  • The user must provide an objective name (lowercase with underscores, e.g. cyclomatic_complexity).
  • Ask the user what is being measured and whether it's a static analysis or performance objective.
  • Follow existing patterns exactly — study lloc.rs (static analysis) and binding.rs (performance) as models.
  • Always run clippy and tests before reporting success. </Execution_Policy>

Phase 1: Gather Requirements

  1. Validate the argument {{ARGUMENTS}}: must be a valid Rust identifier (lowercase alphanumeric + underscores). Reject otherwise.
  2. Ask the user:
    • What is being measured? (becomes the description())
    • Is this a static analysis objective or a performance objective?
      • Static analysis: computes a metric by analyzing source code (e.g. lines of code, complexity). Overrides collect_measurement(), uses Setup = ().
      • Performance: computes a metric by running/profiling some computation (e.g. wall-clock time, max RSS). Overrides setup() and run().
    • What are the units? (e.g. "lines", "s", "bugs")
    • What files/directories does this objective measure? (used for diff_paths() scoping)

Phase 2: Explore Context

  1. Read jolt-eval/src/objective/mod.rs to understand the current enums and dispatch methods.
  2. Read jolt-eval/src/objective/objective_fn/mod.rs to understand objective function registration.
  3. Read an existing objective for reference:
    • Static analysis: jolt-eval/src/objective/code_quality/lloc.rs
    • Performance: jolt-eval/src/objective/performance/binding.rs
  4. If the objective measures jolt-prover-legacy functionality, explore the relevant modules.

Read the full file on GitHub · 136 lines

Files

What ships with it

2 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. 4d ago First seen · 136 lines · 13 tokens per session scan A 376bf4ad8463

Subscribe to this mod's changes

new-objective is a skill published in the GitHub repository a16z/jolt (1,022 stars, last pushed today), licensed Apache-2.0. It adds 13 tokens to every session and 1,316 once invoked, about $0.0001 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 2026-08-30.

Related

Other skills, from other repositories

implementing-zero-knowledge-proof-for-authentication

Zero-Knowledge Proofs (ZKPs) allow a prover to demonstrate knowledge of a secret (such as a password or private key) without revealing the secret itself. This skill implements the Schnorr identificati.

xalgorix/xalgorix · 53 tokens

zkp-toolkit

Zero-Knowledge Proof utilities - proof generation, verification, selective disclosure, ZK-Rollup batching, and benchmarking across ZK systems.

chainlesschain/chainlesschain · 33 tokens

linea-dependency-maintenance

Safely plan and execute dependency maintenance for JavaScript/TypeScript (npm, pnpm) and GitHub Actions, including npm lockfiles, pnpm workspaces, catalogs, overrides, SHA-pinned action versions, release-age policies, audits, CI validation, Dependabot boundaries, PRs, and GitHub tracking issues. Use whenever the user…

Consensys/doc.linea · 113 tokens

pr-content-review

Review docs.linea.build content for editorial compliance (voice, terminology, naming, formatting, frontmatter) before opening or merging a pull request. Use before submitting a PR, when reviewing someone else's draft, or when asked to audit existing pages.

Consensys/doc.linea · 53 tokens

starknet-js

Use when writing or debugging JavaScript/TypeScript that interacts with Starknet through the starknet.js SDK — building Call objects or calldata, encoding/decoding Cairo types (felt252, u256, structs, arrays, spans, ByteArray, Option/Result/custom enums), or working with contracts, accounts, providers, transactions…

starknet-io/starknet.js · 79 tokens

EMILIA Trust Verification

Verify the authenticity of AI-agent authorization receipts and human-device signoffs. Use this whenever a user shares a "trust receipt", an "authorization receipt", a "signoff", or WebAuthn/passkey approval evidence and asks whether it is valid, genuine, or tampered with. Pairs with the public EMILIA Protocol MCP…

emiliaprotocol/emilia-protocol · 94 tokens