Product Capability
affaan-m/ECC
Translate PRD intent, roadmap asks, or product discussions into an implementation-ready capability plan that exposes constraints, invariants, interfaces, and unresolved decisions before…
Estimate whether an AI model can complete a task and how long it will take, using METR-style time-horizon modeling.
Apache-2.0Auto-check passed
Install Capability Horizon Estimator
$ npx skills add tokenbender/agent-guides --skill capability-horizon-estimator -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install tokenbender/agent-guides capability-horizon-estimator --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/tokenbender/agent-guides.git skills-src && mkdir -p .claude/skills && cp -r skills-src/claude-skills/capability-horizon-estimator .claude/skills/capability-horizon-estimator && 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 "capability-horizon-estimator" agent skill from https://github.com/tokenbender/agent-guides/tree/main/claude-skills/capability-horizon-estimator into .claude/skills/capability-horizon-estimator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "capability-horizon-estimator", 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/tokenbender/agent-guides/tree/main/claude-skills/capability-horizon-estimatorType 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 tokenbender/agent-guides --skill capability-horizon-estimator -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install tokenbender/agent-guides capability-horizon-estimator --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tokenbender/agent-guides.git skills-src && mkdir -p .agents/skills && cp -r skills-src/claude-skills/capability-horizon-estimator .agents/skills/capability-horizon-estimator && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "capability-horizon-estimator" agent skill from https://github.com/tokenbender/agent-guides/tree/main/claude-skills/capability-horizon-estimator into .agents/skills/capability-horizon-estimator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "capability-horizon-estimator", 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 tokenbender/agent-guides --skill capability-horizon-estimator -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install tokenbender/agent-guides capability-horizon-estimator --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tokenbender/agent-guides.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/claude-skills/capability-horizon-estimator .cursor/skills/capability-horizon-estimator && 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 "capability-horizon-estimator" agent skill from https://github.com/tokenbender/agent-guides/tree/main/claude-skills/capability-horizon-estimator into .cursor/skills/capability-horizon-estimator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "capability-horizon-estimator", 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/tokenbender/agent-guides.git --path claude-skills/capability-horizon-estimator--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 tokenbender/agent-guides --skill capability-horizon-estimator -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install tokenbender/agent-guides capability-horizon-estimator --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tokenbender/agent-guides.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/claude-skills/capability-horizon-estimator .gemini/skills/capability-horizon-estimator && 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 "capability-horizon-estimator" agent skill from https://github.com/tokenbender/agent-guides/tree/main/claude-skills/capability-horizon-estimator into .gemini/skills/capability-horizon-estimator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "capability-horizon-estimator", 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 tokenbender/agent-guides capability-horizon-estimatorInstalls 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 tokenbender/agent-guides --skill capability-horizon-estimator -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/tokenbender/agent-guides.git skills-src && mkdir -p .github/skills && cp -r skills-src/claude-skills/capability-horizon-estimator .github/skills/capability-horizon-estimator && 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 "capability-horizon-estimator" agent skill from https://github.com/tokenbender/agent-guides/tree/main/claude-skills/capability-horizon-estimator into .github/skills/capability-horizon-estimator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "capability-horizon-estimator", 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 tokenbender/agent-guides --skill capability-horizon-estimator -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install tokenbender/agent-guides capability-horizon-estimator --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tokenbender/agent-guides.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/claude-skills/capability-horizon-estimator .opencode/skills/capability-horizon-estimator && 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 "capability-horizon-estimator" agent skill from https://github.com/tokenbender/agent-guides/tree/main/claude-skills/capability-horizon-estimator into .opencode/skills/capability-horizon-estimator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "capability-horizon-estimator", 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
capability-horizon-estimator- GitHub stars
- 367
- Token cost
- ~1.5k tokens
- SKILL.md length
- 656 words
- Files
- 5 (incl. scripts, references)
- Skills in repo
- 11
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Estimate whether an AI model can complete a task and how long it will take, using METR-style time-horizon modeling.
- Scoping agent work
- SKILL.md covers When to use, The core model, Output format and Calibration rules, plus 1 more section
- Runs Python scripts from its folder
- Deciding if a task is within reach
What it does
Capability Horizon Estimator is an agent skill from tokenbender/agent-guides. Estimate whether an AI model can complete a task and how long it will take, using METR-style time-horizon modeling. Use when scoping agent work, deciding if a task is within reach, planning retries/parallelism, estimating wall-clock time for SWE/MLE/math tasks, or answering "can you do this" / "how long will this take" for autonomous work.
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `README.md`, `references/benchmark-catalog.md` and `references/horizon-data.md`).
The repository describes itself as: one page guides that i let my subscribed/customised agents consume to perform actions. The licence is Apache-2.0.
When your agent uses it
- Scoping agent work
- Deciding if a task is within reach
- Planning retries/parallelism
- Estimating wall-clock time for SWE/MLE/math tasks
Example prompts
- “can you do this”
- “how long will this take”
- “/capability-horizon-estimator”
Requirements
- Python 3
What it can do on your machine
Read from SKILL.md and the folder at commit a74dd9d. 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/ (Python), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
Capability Horizon Estimator loads about 1.5k tokens when it runs, and up to ~3.8k if it reads all its reference files. Until then it costs about 93 tokens; SKILL.md has 656 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 tokenbender/agent-guides at commit a74dd9d, republished under its Apache-2.0 licence (© tokenbender). 656 words, ~1,482 tokens.
Download SKILL.mdSave it as
.claude/skills/capability-horizon-estimator/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- capability-horizon-estimator
- description
- Estimate whether an AI model can complete a task and how long it will take, using METR-style time-horizon modeling. Use when scoping agent work, deciding if a task is within reach, planning retries/parallelism, estimating wall-clock time for SWE/MLE/math tasks, or answering "can you do this" / "how long will this take" for autonomous work.
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 $\beta = 0.8$: $t = h_{50} \Rightarrow p = 50%$ · $t = h_{50}/5.7 \Rightarrow p = 80%$ · $t = 2h_{50} \Rightarrow p \approx 36%$ · $t = 4h_{50} \Rightarrow p \approx 25%$.
Step 4 — Difficulty adjustments (multiply $t$ before Step 3).
| Condition | Multiplier on $t$ |
|---|---|
| Well-specified, auto-verifiable (benchmark-like) | ×1 |
| Proprietary/large codebase, high prior context needed | ×2 |
| Messy, underspecified, human-judged success | ×4 (range ×2–8) |
| GUI/computer-use (no API/DOM) | ×50–100 — different capability cluster |
| Parallelizable/additive work (N independent items) | Not one task — split, apply model per piece |
Rationale: METR's suite is clean and self-contained; models do measurably worse on messy tasks and under holistic (vs algorithmic) scoring. GUI horizons measured ~40–100× shorter than SWE/reasoning.
Step 5 — "Pushed itself" uplift.
- Better scaffold/elicitation: ×1.5–2 on $h_{50}$ (scaffold choice moves measured horizons ~2×)
- Best-of-N independent attempts: $P(\geq 1 \text{ success}) = 1 - (1-p)^N$
- Both compose. A $p = 0.25$ task with a good scaffold ($\times 1.75 h$) and 6 attempts: $p \to \sigma(0.8 \ln(1.75 \cdot h/t)) \approx 0.37$ per attempt, $1-(1-0.37)^6 \approx 94%$.
Step 6 — Wall-clock time. Agents complete tasks they can do several times faster than the human baseline:
$$\text{wall-clock} \approx \frac{t_{\text{human}}}{S} \times \text{expected attempts}, \quad S \approx 3\text{–}8\times \text{ for SWE (default 5)}$$
Expected attempts $= 1/p$ for independent retries (cap at 3–5 in practice; if it fails 3×, the plan is wrong, not the luck). Report a range, not a point.
Show full SKILL.md (177 more words)Show less
Output format
TASK: <one line>
HUMAN-EQUIVALENT TIME (t): <estimate> (anchor: <reference task>)
MODEL HORIZON (h50): <value> (source: table / extrapolated from <date>, D=150d)
DIFFICULTY: ×<mult> (<reason>) → effective t = <value>
SINGLE-ATTEMPT SUCCESS: <p> → <verdict>
PUSHED (scaffold ×1.75, N=<n>): <p_eff> per attempt, <P> overall
WALL-CLOCK ESTIMATE: <range> (t/S × attempts, S=5)
VERDICT: CONFIDENT (≥80%) | LIKELY (60–80%) | COIN-FLIP (35–60%) | STRETCH (15–35%) | OUT OF REACH (<15%)
CAVEATS: <extrapolation flags, messiness, jagged-domain warnings>
DECOMPOSITION ADVICE: <if stretch/out-of-reach: where to split>Calibration rules
- Always state the anchor. Every $t$ estimate names the reference task it was derived from. No anchor, no number.
- Report ranges. Horizons have wide CIs (Opus 4.6 p50: 317–3634 min). Give the interval, pick the geometric mean for the headline.
- Above 16 h human-equivalent, say so. METR's suite saturates at 16 h; estimates beyond it are extrapolation, not measurement.
- Jaggedness is real. A model strong in SWE may be 50–100× weaker on GUI work, and different on math research. Never transfer a horizon across domains without the multiplier.
- Long ≠ hard, hard ≠ long. The model applies to coherent, non-parallelizable tasks. 1000 independent 1-hour problems is a 1-hour task done 1000 times.
- Failure mode asymmetry. Near the horizon, models fail by derailing (repeating failed approaches, losing state), not by slow progress. If $p < 50%$, recommend decomposition over retries.
Reference files
references/horizon-data.md— METR TH v1.1 per-model p50/p80 table (2019 → May 2026), doubling-time stats, methodology caveatsreferences/benchmark-catalog.md— SWE/MLE/math benchmark inventory with task times, human budgets, and July-2026 SOTAscripts/estimate.py— calculator for Steps 3–6 (logistic p, best-of-N, wall-clock)
© tokenbender, 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 4 other files (scripts, references) in claude-skills/capability-horizon-estimator of tokenbender/agent-guides.
- SKILL.md
- README.md
- references/benchmark-catalog.md
- references/horizon-data.md
- scripts/estimate.py
Open the folder on GitHubat commit a74dd9d
Compare with similar skills
Capability Horizon Estimator 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 |
|---|---|---|---|---|---|---|
| Capability Horizon Estimator this skilltokenbender/agent-guides | 367 | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | |
| Product Capabilityaffaan-m/ECC | 275k | 2 repos | ~1.1k | Automated safety check: Pass | MIT | |
| Horizon Trackruvnet/ruflo | 74k | — | ~744 | Automated safety check: Notes | MIT | |
| Artifact Capabilitiesasgeirtj/system_prompts_leaks | 69k | — | ~4.3k | Automated safety check: Pass | CC0-1.0 | |
| Configuring Horizoncoollabsio/coolify | 63k | 4 repos | ~898 | Automated safety check: Pass | MIT | |
| Task Effort EstimatorDonchitos/Claude-Code-Game-Studios | 26k | — | ~1.2k | Automated safety check: Pass | MIT |
Similar skills
Horizon Track
ruvnet/ruflo
Track long-horizon objectives across multiple sessions with milestone checkpoints, progress persistence, and drift detection
Artifact Capabilities
asgeirtj/system_prompts_leaks
Runtime capabilities a published Artifact page can be granted — behavior static HTML cannot provide on its own, such as the page reading live or connected data, remembering what people do on it (a…
Configuring Horizon
coollabsio/coolify
A skill your agent uses whenever the user mentions Horizon by name in a Laravel context.
Task Effort Estimator
Donchitos/Claude-Code-Game-Studios
Estimates the effort for a game development task from code complexity, scope, risk and past sprint data, returning a range with a confidence level.
Product Capability
affaan-m/ECC
将PRD意图、路线图需求或产品讨论转化为可实施的方案计划，在开始多服务工作之前暴露约束、不变性、接口和未解决的决策。当用户需要ECC原生的PRD到SRS通道，而不是模糊的规划文本时使用。
More from tokenbender/agent-guides
All 11 skills in this repoTechnical Writing Workflow
tokenbender/agent-guides
A skill your agent uses for planning, researching, drafting, revising, or auditing technical write-ups, textbooks, papers, reports, READMEs, research notes, PR narratives, and public technical prose.
Epistemic Libido
tokenbender/agent-guides
Filter, compare, and rank papers, posts, captures, threads, bookmarks, product claims, or research ideas for high-entropy mechanistic insight and underpriced leverage.
Manim Math Explainer
tokenbender/agent-guides
Trigger when: (1) the user asks for Manim, Manim Community, or ManimCE, (2) code contains from manim import , or (3) the task is to build a mathematical explainer animation.
Worklog
tokenbender/agent-guides
Issue-led atomic work logging. An agent skill from tokenbender/agent-guides.
X Thread Reader
tokenbender/agent-guides
A skill your agent uses when the user provides an X/Twitter status URL and needs the full thread, context beyond the first post, comparison, summary, intent analysis, title extraction, or reliable…
Audit Sft Data Quality
tokenbender/agent-guides
Audit supervised fine-tuning datasets against the behavior and task they are meant to teach.
Questions about Capability Horizon Estimator
What does Capability Horizon Estimator do?
Estimate whether an AI model can complete a task and how long it will take, using METR-style time-horizon modeling. Capability Horizon Estimator is an agent skill from tokenbender/agent-guides. Estimate whether an AI model can complete a task and how long it will take, using METR-style time-horizon modeling.
When should I use Capability Horizon Estimator?
Capability Horizon Estimator fits situations like: scoping agent work; deciding if a task is within reach; planning retries/parallelism; estimating wall-clock time for SWE/MLE/math tasks.
How do I install Capability Horizon Estimator in Claude Code?
Run `npx skills add tokenbender/agent-guides --skill capability-horizon-estimator -a claude-code`. Or copy the skill folder (claude-skills/capability-horizon-estimator in tokenbender/agent-guides) into .claude/skills/capability-horizon-estimator in your project. Claude Code loads it when a task matches its description.
How do I install Capability Horizon Estimator in Codex?
Run `npx skills add tokenbender/agent-guides --skill capability-horizon-estimator -a codex`. Or copy the skill folder (claude-skills/capability-horizon-estimator in tokenbender/agent-guides) into .agents/skills/capability-horizon-estimator in your project. Codex loads it when a task matches its description.
Can I use Capability Horizon Estimator 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 tokenbender/agent-guides --skill capability-horizon-estimator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/capability-horizon-estimator, .gemini/skills/capability-horizon-estimator, .github/skills/capability-horizon-estimator and .opencode/skills/capability-horizon-estimator in your project.
What does Capability Horizon Estimator need to run?
Going by SKILL.md and its folder, Capability Horizon Estimator needs Python for the scripts in its folder. Our summary lists: Python 3.
Does Capability Horizon Estimator access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Capability Horizon Estimator 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 Capability Horizon Estimator use?
Capability Horizon Estimator 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 Capability Horizon Estimator use?
About 1.5k tokens (SKILL.md is roughly 5.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.3k tokens, read only when the agent opens those files.
What are the alternatives to Capability Horizon Estimator?
Skills that share tags, products or a category with Capability Horizon Estimator: Product Capability (affaan-m/ECC, 275k stars), Horizon Track (ruvnet/ruflo, 74k stars), Artifact Capabilities (asgeirtj/system_prompts_leaks, 69k stars) and Configuring Horizon (coollabsio/coolify, 63k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Capability Horizon Estimator?
tokenbender (a GitHub user) maintains it in tokenbender/agent-guides, which has 367 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on July 23, 2026.
Source: tokenbender/agent-guides on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.