New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Since Cutoff

by hashgraph-online in hashgraph-online/awesome-codex-plugins

Find which dependency APIs this project's Python code uses changed after the model's training cutoff (no model calls), write short AGENTS.md or CLAUDE.md notes from the API diff, each with its…

MITAuto-check passedAgent Workflows

Install Since Cutoff

skills CLI
$ npx skills add hashgraph-online/awesome-codex-plugins --skill since-cutoff -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install hashgraph-online/awesome-codex-plugins since-cutoff --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/MohammadHijjawi97/since-cutoff/skills/since-cutoff .claude/skills/since-cutoff && rm -rf skills-src

Use ~/.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/

Facts

Skill name
since-cutoff
GitHub stars
1.3k
Token cost
~2.5k tokens
SKILL.md length
1,301 words
Files
1
Skills in repo
714
Repo updated
First seen
Licence
MIT

At a glance

Find which dependency APIs this project's Python code uses changed after the model's training cutoff (no model calls), write short AGENTS.md or CLAUDE.md notes from the API diff, each with its…

  • Works in 7 steps: Work from the project root (the… → Pick the command. Use the arguments the… → Name the model. Without --model, the… → …
  • The user asks whether the model knows their library versions
  • SKILL.md covers Overview, Prerequisites, Instructions and Output, plus 4 more sections
  • Calls uvx and pipx

What it does

Since Cutoff is an agent skill from hashgraph-online/awesome-codex-plugins. Find which dependency APIs this project's Python code uses changed after the model's training cutoff (no model calls), write short AGENTS.md or CLAUDE.md notes from the API diff, each with its source, and keep them in step with the lockfile; optionally measure which of the changes the model gets wrong. Use when the user asks whether the model knows their library versions, when code keeps failing on renamed or removed library APIs, or after upgrading dependencies. Trigger with requests such as "does the model know…

Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: Needs since-cutoff on PATH, or uv or pipx to run it, and network access to PyPI. The run command also needs model access (the claude CLI or a provider API…

It sits in Agent Workflows, covering Agent instruction files and Dependency management. It works with Python and OpenAI. The repository describes itself as: A curated list of awesome OpenAI Codex / ChatGPT plugins, skills, and resources. The 1 Codex Marketplace. See live plugins at: https://hol.org/plugins/best-codex-plugins. The licence is MIT.

When your agent uses it

  • The user asks whether the model knows their library versions
  • Code keeps failing on renamed
  • Removed library APIs
  • After upgrading dependencies

Example prompts

  • “s Python code uses changed after the model”
  • “does the model know my openai version”
  • “scan my dependencies for API changes”
  • “/since-cutoff”

Requirements

  • Python 3
  • Compatibility (from SKILL.md): Needs since-cutoff on PATH, or uv or pipx to run it, and network access to PyPI. The run command also needs model access (the claude CLI or a provider API key); scan, sync and status make no model calls, and status works offline.
  • Pre-approved tools (allowed-tools): Bash(since-cutoff scan:*), Bash(since-cutoff sync:*), Bash(since-cutoff status:*), Bash(since-cutoff run:*), Bash(since-cutoff models:*), Bash(since-cutoff unapply:*), Bash(uvx since-cutoff:*), Bash(pipx run since-cutoff:*), Read

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Work from the project root (the directory with pyproject.toml, requirements.txt or a lockfile).
  2. Pick the command. Use the arguments the user gave, if any (scan, sync, status or run,
  3. Name the model. Without --model, the tool tests the model your coding agent is set up with
  4. Before run, tell the user that it sends prompts (package names, versions, public API
  5. Run it. If since-cutoff is not installed, use uvx since-cutoff with the same arguments
  6. Summarise the result card: the model and its training cutoff, how many dependencies changed
  7. Only write notes into the user's files if they asked for it. After scan, run

What it can do on your machine

Read from SKILL.md and the folder at commit 9e7b281. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash(since-cutoff scan:*)
    • Bash(since-cutoff sync:*)
    • Bash(since-cutoff status:*)
    • Bash(since-cutoff run:*)
    • Bash(since-cutoff models:*)
    • Bash(since-cutoff unapply:*)
    • Bash(uvx since-cutoff:*)
    • Bash(pipx run since-cutoff:*)
    • Read

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • uvx
    • pipx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    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.

  • Compatibility

    Needs since-cutoff on PATH, or uv or pipx to run it, and network access to PyPI. The run command also needs model access (the claude CLI or a provider API key); scan, sync and status make no model calls, and status works offline.

    From compatibility in the SKILL.md frontmatter.

Context cost

Since Cutoff loads about 2.5k tokens when it runs. Until then it costs about 161 tokens; SKILL.md has 1,301 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~161
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from hashgraph-online/awesome-codex-plugins at commit 9e7b281, republished under its MIT licence (© hashgraph-online). 1,301 words, ~2,475 tokens.

Download SKILL.mdSave it as .claude/skills/since-cutoff/SKILL.md (or your agent's skills folder).
name
since-cutoff
description
Find which dependency APIs this project's Python code uses changed after the model's training cutoff (no model calls), write short AGENTS.md or CLAUDE.md notes from the API diff, each with its source, and keep them in step with the lockfile; optionally measure which of the changes the model gets wrong. Use when the user asks whether the model knows their library versions, when code keeps failing on renamed or removed library APIs, or after upgrading dependencies. Trigger with requests such as "does the model know my openai version", "scan my dependencies for API changes" or "check whether the library notes are up to date".
allowed-tools
Bash(since-cutoff scan:*), Bash(since-cutoff sync:*), Bash(since-cutoff status:*), Bash(since-cutoff run:*), Bash(since-cutoff models:*), Bash(since-cutoff unapply:*), Bash(uvx since-cutoff:*), Bash(pipx run since-cutoff:*), Read
compatibility
Needs since-cutoff on PATH, or uv or pipx to run it, and network access to PyPI. The run command also needs model access (the claude CLI or a provider API key); scan, sync and status make no model calls, and status works offline.
license
MIT
metadata.author
Mohammad Hijjawi
metadata.version
0.5.0

since-cutoff

since-cutoff is a command-line tool that finds the APIs a project's dependencies changed after the model's training cutoff and writes notes about them, each with its source. Run the tool and report what it prints.

Overview

  • since-cutoff scan compares, for each dependency, the public API of the latest release on or before the model's training cutoff with the version the project pins (a static diff, no model calls), and lists the changed APIs the code uses.
  • since-cutoff sync writes notes from that diff into a marked block in AGENTS.md or CLAUDE.md and keeps them in step with the lockfile; since-cutoff status checks the block offline, and since-cutoff unapply removes it.
  • since-cutoff run is optional. It does the measuring itself by calling a fresh copy of the model with no tools and no project context, so do not answer the probe tasks yourself and do not guess results.

Prerequisites

  • A Python project with its dependencies in pyproject.toml, requirements.txt or a lockfile.
  • since-cutoff on PATH, or uv or pipx to run it (uvx since-cutoff, pipx run since-cutoff).
  • Network access to PyPI; status works offline.
  • For run only: model access, through the claude CLI for Claude Code models or the provider's API key for other models. scan, sync and status make no model calls.

Instructions

  1. Work from the project root (the directory with pyproject.toml, requirements.txt or a lockfile).
  2. Pick the command. Use the arguments the user gave, if any (scan, sync, status or run, with flags such as --apply, --quick or --model); otherwise:
    • quick look, no model calls: since-cutoff scan (then offer sync, step 7)
    • full measurement, with notes a model writes and keeps only when their example type-checks: since-cutoff run --quick
  3. Name the model. Without --model, the tool tests the model your coding agent is set up with (SINCE_CUTOFF_MODEL; inside Claude Code, only Claude Code's settings; elsewhere the Claude Code, Codex, Gemini CLI, OpenCode and Aider settings, the project's before the user's) and says where it read it ("model from ..."). If that is not the model you are, or it warns that no model setting was found, add --model PROVIDER:MODEL for the model you are (for example --model openai:gpt-5.4, or --model claude-code:MODEL for a model picked with /model). run calls Claude Code models through the claude CLI and other models through their provider's API key.
  4. Before run, tell the user that it sends prompts (package names, versions, public API signatures and generated tasks, never their source code) to the model provider they choose, uses their API credits or Claude Code usage, and can take 5-20 minutes. Wait for a yes. scan needs no confirmation.
  5. Run it. If since-cutoff is not installed, use uvx since-cutoff with the same arguments (or use pipx run since-cutoff). Start run in the background or with a long timeout, not a 2-minute foreground call. Everything is cached, so re-running after an interruption resumes quickly.
  6. Summarise the result card: the model and its training cutoff, how many dependencies changed after the cutoff, what was stale, and the held-out before/after numbers. Quote each interval with the number it belongs to: the bootstrap CI goes with the difference of the task-level rates, the other CI with "changes fixed: X of Y". If the run compared baseline notes (--compare), give each block's "changes fixed" with its CI, and call one block better only when report.md's head-to-head sign test for it has a small p-value.
  7. Only write notes into the user's files if they asked for it. After scan, run since-cutoff sync --dry-run, show the user the diff it prints, and only when they agree run since-cutoff sync --yes: it writes the notes from the API diff into a marked block in AGENTS.md (or CLAUDE.md if that is the file the project uses) and, run again later, keeps them in step with the lockfile. When scan suggests sync --scope imported (the code uses none of the changed APIs yet), add it to both commands. After run, --apply writes that run's notes in place of the whole block; since-cutoff sync then adds the notes from the diff for the other changed APIs the code uses, keeping the run's [type-checked] ones. since-cutoff unapply removes the block again. since-cutoff status says, without the network, whether the notes still match the lockfile; from since-cutoff 0.4.0 the Claude Code plugin runs it when a session starts (the first time, uvx downloads since-cutoff).
Show full SKILL.md (569 more words)Show less

Output

  • The terminal: the model, its training cutoff and where the tool read the model, the dependencies that changed after the cutoff, and the changed APIs the code uses, each with its note. run adds the result card of step 6.
  • .since-cutoff/report.md: the full report. Read it when the user wants details.
  • The notes block in AGENTS.md or CLAUDE.md, written only by sync --yes or run --apply. The notes in it are API reference facts about the versions the project pins: what was removed, renamed or deprecated after the release at your training cutoff, each tagged with what was checked, for example [diff] (a static comparison of the two releases' public APIs), [diff + library] (the library's own deprecation text names the replacement), [diff + move checked], [diff + metadata] (the two releases' Requires-Dist: the package requires another library, such as httpx2 instead of httpx, and its API takes that library's types), [diff; probable rename] (a guess, labelled as one) or [type-checked] (written during run; its example passed the type check). Check them when you write code that uses those libraries, and claim no more than the tag says.

Error Handling

  • No lockfile or pinned versions found: tell the user which file the tool asked for; do not invent versions.
  • A model or login error during run: report the message and offer scan, which makes no model calls.
  • sync exits with code 4: the block was edited by hand. Tell the user, and pass --force only if they say so.
  • sync without --yes asks on the terminal; with no terminal to ask in it writes nothing and exits with code 3. Show the --dry-run diff and use --yes once the user agrees.
  • status exits with code 3 when the notes are out of date: offer sync as in step 7.
  • run was interrupted: run the same command again; it resumes from the cache.

Examples

Example 1: "Does the model know the library versions this project pins?"

bash
since-cutoff scan

Summarise what it lists. If the user wants notes, show the diff and write once they agree:

bash
since-cutoff sync --dry-run
since-cutoff sync --yes

Example 2: "Measure which of these changes you get wrong, and add the notes."

Tell the user what run sends, what it costs and how long it takes (step 4). After a yes, start it in the background (with --model if step 3 calls for it), then show the notes sync would add for the other changed APIs:

bash
since-cutoff run --quick --apply
since-cutoff sync --dry-run

Example 3: "I upgraded openai. Are the notes in AGENTS.md still right?"

bash
since-cutoff status

If the notes are out of date, show the diff of since-cutoff sync --dry-run and run since-cutoff sync --yes once the user agrees; to remove them, since-cutoff unapply.

Quick lookups without a run

If the since-cutoff MCP server is connected (the Claude Code plugin starts it), its tools answer from a static diff, with no model calls: api_changes (one package, optionally one symbol), project_changes (every dependency of the project) and model_cutoff. Pass your own model id as model. Use them before writing code against a dependency that may be newer than your training data; use the CLI above when the user wants the model measured or notes written.

Resources

  • since-cutoff on GitHub: the README, with every command, flag and exit code, and what each note tag means.
  • How it works: the diff, the notes and the measurement in detail.
  • Privacy: what run sends to the model provider, and what stays on the machine.
  • Changelog: what changed in each release.

© hashgraph-online, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/MohammadHijjawi97/since-cutoff/skills/since-cutoff of hashgraph-online/awesome-codex-plugins.

Open the folder on GitHubat commit 9e7b281

Compare with similar skills

Since Cutoff 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.

Since Cutoff compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Since Cutoff this skillhashgraph-online/awesome-codex-plugins1.3k—~2.5kAutomated safety check: PassMIT
Codex CLI Bridgealirezarezvani/claude-code-skill-factory880—~2.2kAutomated safety check: PassMIT
Mspm0 Ccsmc3545dada/mspm0-skill374—~4.5kAutomated safety check: PassMIT
Remember Learningsdyad-sh/dyad22k—~1.1kAutomated safety check: PassCustom licence
Generate AI Rulesdivar-ir/ai-doc-gen767—~1.2kAutomated safety check: PassMIT
Goal Prompt Builderwin4r/goal-prompt-builder229—~3.1kAutomated safety check: PassMIT

Similar skills

  • Codex CLI Bridge

    alirezarezvani/claude-code-skill-factory

    Bridge between Claude Code and OpenAI Codex CLI - generates AGENTS.md from CLAUDE.md, provides Codex CLI execution helpers, and enables seamless interoperability between both tools

    880 GitHub stars~2.2k tokensUpdated 11 mo ago
    Agent WorkflowsAuto-check passed

  • Mspm0 Ccs

    mc3545dada/mspm0-skill

    Tool-neutral CLI agent rules for TI MSPM0 development with Code Composer Studio, Keil/uVision, CMake/GCC/OpenOCD, SysConfig, and DriverLib.

    374 GitHub stars~4.5k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed

  • Remember Learnings

    dyad-sh/dyad

    Review the current session for errors, issues, snags, and hard-won knowledge, then update the rules/ files (or AGENTS.md if no suitable rule file exists) with actionable learnings.

    22k GitHub stars~1.1k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Generate AI Rules

    divar-ir/ai-doc-gen

    Generate AI assistant configuration files for a repository — CLAUDE.md, AGENTS.md, and Cursor rules (.cursor/rules/.mdc) — from codebase analysis.

    767 GitHub stars~1.2k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed

  • Goal Prompt Builder

    win4r/goal-prompt-builder

    Build high-quality /goal commands for OpenAI Codex CLI 0.128+ that maximize audit-friendliness and minimize false-completion.

    229 GitHub stars~3.1k tokensUpdated 5 mo ago
    Agent WorkflowsAuto-check passed

  • Requirement Ledger CLI Workflow

    adand-91/gpt-6-astra-skill

    Runs an evidence-bound audit, daily or weekly review through the requirement-ledger CLI, binding scope and authority first and blocking the final report until a handoff check passes.

    126 GitHub stars~1.5k tokensUpdated 23 days ago
    Agent WorkflowsAuto-check passed

More from hashgraph-online/awesome-codex-plugins

All 714 skills in this repo

  • Anime Reaction Gif

    hashgraph-online/awesome-codex-plugins

    Create original anime-style reaction stickers as looping GIFs and MP4 previews, using generated character pose sheets and timed key poses.

    1.3k GitHub stars~922 tokensUpdated today
    Auto-check passed

  • Calibredb

    hashgraph-online/awesome-codex-plugins

    Manage and query Calibre libraries with the calibredb CLI (local paths or Calibre Content server URLs).

    1.3k GitHub stars~1k tokensUpdated today
    Auto-check passed

  • Rust API Test Harness

    hashgraph-online/awesome-codex-plugins

    A skill your agent uses when adding, changing, testing, or debugging Rust HTTP APIs and services, especially when Codex needs black-box integration tests, random-port app startup, real database test…

    1.3k GitHub stars~1.7k tokensUpdated today
    Auto-check passed

  • Art

    hashgraph-online/awesome-codex-plugins

    Make a studio's game look like something at build time — a cover from a real frame of the game (free), painted covers, backdrops, textures and character plates from image models through the…

    1.3k GitHub stars~2.4k tokensUpdated today
    Auto-check passed

  • Calle

    hashgraph-online/awesome-codex-plugins

    Use CALL-E from Codex through the calle CLI. An agent skill from hashgraph-online/awesome-codex-plugins.

    1.3k GitHub stars~2.9k tokensUpdated today
    Auto-check passed

  • Game Balance Economy

    hashgraph-online/awesome-codex-plugins

    Balance game difficulty, resources, rewards, probability, progression, economies, and dominant strategies.

    1.3k GitHub stars~618 tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Since Cutoff

What does Since Cutoff do?

Find which dependency APIs this project's Python code uses changed after the model's training cutoff (no model calls), write short AGENTS.md or CLAUDE.md notes from the API diff, each with its…. Since Cutoff is an agent skill from hashgraph-online/awesome-codex-plugins.md notes from the API diff, each with its source, and keep them in step with the lockfile; optionally measure which of the changes the model gets wrong.

When should I use Since Cutoff?

Since Cutoff fits situations like: the user asks whether the model knows their library versions; code keeps failing on renamed; removed library APIs; after upgrading dependencies.

How do I install Since Cutoff in Claude Code?

Run `npx skills add hashgraph-online/awesome-codex-plugins --skill since-cutoff -a claude-code`. Or copy the skill folder (plugins/MohammadHijjawi97/since-cutoff/skills/since-cutoff in hashgraph-online/awesome-codex-plugins) into .claude/skills/since-cutoff in your project. Claude Code loads it when a task matches its description.

How do I install Since Cutoff in Codex?

Run `npx skills add hashgraph-online/awesome-codex-plugins --skill since-cutoff -a codex`. Or copy the skill folder (plugins/MohammadHijjawi97/since-cutoff/skills/since-cutoff in hashgraph-online/awesome-codex-plugins) into .agents/skills/since-cutoff in your project. Codex loads it when a task matches its description.

Can I use Since Cutoff 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 hashgraph-online/awesome-codex-plugins --skill since-cutoff -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/since-cutoff, .gemini/skills/since-cutoff, .github/skills/since-cutoff and .opencode/skills/since-cutoff in your project.

What does Since Cutoff need to run?

Going by SKILL.md and its folder, Since Cutoff needs the command-line tools its instructions call (uvx and pipx). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Bash(since-cutoff scan:*), Bash(since-cutoff sync:*), Bash(since-cutoff status:*), Bash(since-cutoff run:*), Bash(since-cutoff models:*), Bash(since-cutoff unapply:*), Bash(uvx since-cutoff:*), Bash(pipx run since-cutoff:*), Read. Compatibility (from SKILL.md): Needs since-cutoff on PATH, or uv or pipx to run it, and network access to PyPI. The run command also needs model access (the claude CLI or a provider API key); scan, sync and status make no model calls, and status works offline..

Does Since Cutoff access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Since Cutoff 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. Review the folder before installing.

What licence does Since Cutoff use?

Since Cutoff is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Since Cutoff use?

About 2.5k tokens (SKILL.md is roughly 9.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Since Cutoff?

Skills that share tags, products or a category with Since Cutoff: Codex CLI Bridge (alirezarezvani/claude-code-skill-factory, 880 stars), Mspm0 Ccs (mc3545dada/mspm0-skill, 374 stars), Remember Learnings (dyad-sh/dyad, 22k stars) and Generate AI Rules (divar-ir/ai-doc-gen, 767 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Since Cutoff?

hashgraph-online (a GitHub organization) maintains it in hashgraph-online/awesome-codex-plugins, which has 1,255 GitHub stars. The repository holds 714 skills in this directory. The repository was last updated on October 9, 2026.

Source: hashgraph-online/awesome-codex-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.