capability-horizon-estimator

capability-horizon-estimator is a skill for Claude Code, Codex from tokenbender/agent-guides. It costs 84 tokens per session (1,783 once invoked), scanned A, original, Apache-2.0.

A framework for estimating whether an AI model can finish a task and how long the work may take. It uses METR-style time horizons, which compare a task's estimated human effort with a model's demonstrated ability to complete tasks of different lengths.

In plain words
What is it for?
Use it to scope coding, machine-learning, or mathematics work, estimate agent run time, choose retry or parallel-work budgets, and answer whether a task is likely within reach.
Why use it?
It replaces vague confidence with a rough success estimate and helps reveal when a task should be split into smaller parts or given more attempts.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Use it to scope coding, machine-learning, or mathematics work, estimate agent run time, choose retry or parallel-work budgets, and answer whether a task is likely within reach.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tokenbender/agent-guides/capability-horizon-estimator
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.

Any agent
npx skills add tokenbender/agent-guides --skill capability-horizon-estimator
Clone the repo
git clone --depth 1 https://github.com/tokenbender/agent-guides

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 capability-horizon-estimator

README.md
[![agentmods](https://agentmods.dev/badge/skills/tokenbender/agent-guides/capability-horizon-estimator.svg)](https://agentmods.dev/skills/tokenbender/agent-guides/capability-horizon-estimator)
Your own site
<a href="https://agentmods.dev/skills/tokenbender/agent-guides/capability-horizon-estimator"><img src="https://agentmods.dev/badge/skills/tokenbender/agent-guides/capability-horizon-estimator.svg" alt="Measured on agentmods" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,783 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00084 $0.01783
Opus 5 $0.00042 $0.00892
Sonnet 5 $0.00017 $0.00357
Haiku 4.5 $0.00008 $0.00178

Measured 8d ago against content hash dfc79b572f0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

capability-horizon-estimator 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/estimate.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/capability-horizon-estimator/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Capability & Time Horizon Estimator

Estimate what a model can do and how long it takes using the METR time-horizon framework: every task has a human-equivalent duration $t$, every model has a 50% time horizon $h_{50}$, and success probability follows a logistic curve in $\log(h/t)$.

When to use

  • "Can you do X autonomously?" — give a calibrated yes/maybe/no instead of vibes
  • "How long will this agent run take?" — wall-clock estimate with retry overhead
  • Scoping: should this be one task, or decomposed?
  • Deciding attempt budget (best-of-N) for a stretch task

The core model

Step 1 — Estimate human-equivalent task time $t$ (minutes). Anchor against known reference points (full table in references/benchmark-catalog.md):

Reference task Human time
SWE-bench Verified issue 7 min – 2 h
HCAST task bands 15 min / 1 h / 4 h / 8 h
RE-Bench ML research task 8 h
Small bug fix, clear repro 15–60 min
Multi-file feature 2–8 h
Cross-repo refactor 4–16 h
Kaggle competition (MLE-bench) days of human effort
FrontierMath T4 problem days–weeks of expert time

Estimate for a low-context professional (new hire, contractor), not the resident expert — that is what the horizons are calibrated against.

Step 2 — Get the model's horizon $h_{50}$ (minutes). Look it up in references/horizon-data.md (METR TH v1.1, May 2026). If the model isn't listed, extrapolate from release date:

$$h_{50}(\text{date}) = h_{50}(\text{ref}) \times 2^{(\text{date} - \text{ref}) / D}, \quad D \approx 130\text{–}190 \text{ days}$$

Use $D = 150$ days as default; state the range. Post-2024 data supports faster ($\sim$90–130 days); all-time average is $\sim$190.

Step 3 — Success probability.

$$p = \sigma!\big(\beta \cdot \ln(h_{50}/t)\big), \quad \beta \approx 0.8 \text{ (range 0.6–0.9)}, \quad \sigma(x) = \frac{1}{1+e^{-x}}$$

Sanity anchors with $\beta = 0.8$: $t = h_{50} \Rightarrow p = 50%$ · $t = h_{50}/5.7 \Rightarrow p = 80%$ · $t = 2h_{50} \Rightarrow p \approx 36%$ · $t = 4h_{50} \Rightarrow p \approx 25%$.

Read the full file on GitHub · 102 lines

Files

What ships with it

4 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. 8d ago First seen · 102 lines · 84 tokens per session scan A dfc79b572f0b

Subscribe to this mod's changes

capability-horizon-estimator is a skill published in the GitHub repository tokenbender/agent-guides (368 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 84 tokens to every session and 1,783 once invoked, about $0.0004 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

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…

openai/codex · 114 tokens