New: 97,000+ 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

Plan Change

by epam in epam/cloud-pipeline

Plan the work before you edit — its phases, the model and effort each takes, and whether it is worth a plan file with a ledger beside it.

Apache-2.0Auto-check passed

Install Plan Change

skills CLI
$ npx skills add epam/cloud-pipeline --skill plan-change -a claude-code

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

GitHub CLI
$ gh skill install epam/cloud-pipeline plan-change --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/epam/cloud-pipeline.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/plan-change .claude/skills/plan-change && 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
plan-change
GitHub stars
162
Token cost
~1.4k tokens
SKILL.md length
721 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
Apache-2.0

At a glance

Plan the work before you edit — its phases, the model and effort each takes, and whether it is worth a plan file with a ledger beside it.

  • SKILL.md covers The plan and The ledger
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Plan Change is an agent skill from epam/cloud-pipeline. Plan the work before you edit — its phases, the model and effort each takes, and whether it is worth a plan file with a ledger beside it. Also when resuming a plan, or told to continue one.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Cloud agnostic genomics analysis, scientific computation and storage platform. The licence is Apache-2.0.

Example prompts

  • “/plan-change”

What it can do on your machine

Read from SKILL.md and the folder at commit 5017688. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml and markdown).

    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

Plan Change loads about 1.4k tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 721 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~50
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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 epam/cloud-pipeline at commit 5017688, republished under its Apache-2.0 licence (© epam). 721 words, ~1,447 tokens.

Download SKILL.mdSave it as .claude/skills/plan-change/SKILL.md (or your agent's skills folder).
name
plan-change
description
Plan the work before you edit — its phases, the model and effort each takes, and whether it is worth a plan file with a ledger beside it. Also when resuming a plan, or told to continue one.

Planning a change

A plan is two files: the plan, and a ledger beside it recording what actually happened. Most tasks need neither — state the plan, get a yes, start editing; nothing goes to disk. Write the files whenever you are asked, and when the work spans more than one session, branch or pull request. Resuming beats re-deriving, so look first: the prompt normally names the plan, and on a bare "implement the plan" search both directories below, asking which if several match.

PathTracked
.agents/plans.local/<key>/<slug>.md, its <slug>.ledger.md beside itno — the default
.agents/plans/<key>/<slug>.md, its <slug>.ledger.md beside ityes — once shared

<key> is whatever identifies the work — issue_<n>, the branch name (its / nests as a path), or a short feature slug — and it is a directory, not a filename: one key can carry several plans, each with its own ledger. Share one — move both files into .agents/plans/ — when it outlives the branch or someone else must read it; attended, ask first. Unattended, leave it local: the plan goes in the pull request body. Never retire a shared plan on your own initiative; a merged pull request does not mean the issue is done.

The plan

Frontmatter, then phases, in order. The body is otherwise whatever the change needs.

yaml
---
issue: 4538                                    # or `none`, with why in the body
branch: issue_4538/restore_storage_prompt_gui  # exact, per CONTRIBUTIONS.md
base: develop-agentic @ 7b2cc2ccce             # `tbd` until Workspace establishes it
area: gui                                      # say in the body which phases leave it
author: Cloud Pipeline Agent
model: <model>                                 # the one writing the plan; the ledger records what ran
cadence: checkpoint                            # continue · checkpoint · delegated — see below
location: local
---

All eight are required of a plan you write — tbd and none are answers, a missing key is not. A plan a person wrote owes none of this: read it as it is, and never restructure it to fit.

Each phase opens by advising a role and effort — implementer · medium — mechanical, one file per test target. Advice, not a decision. Effort is one of low, medium, high, xhigh, max. Record the model that actually ran in the ledger, not here.

Amend the plan in place when a decision makes a later phase's text wrong, and say so in the ledger: the plan stays the thing you can execute, the ledger stays why it changed. The plan holds what you assumed while planning; the ledger holds what working proved.

How it gets executed is part of it, so ask while writing it, attended, and record the answer in cadence:. Every mode is one commit per phase, plus the ledger's own commit last.

cadence:
continuethe phases run back to back, no stop between them
checkpointafter each phase, report and stop, ending with a one-line prompt to resume: continue <plan path> phase <n>
delegatedone sub-agent per phase, launched one at a time, each on a fresh context; no stop

Unattended — the implement-task skill defines when — use delegated where this session can launch a fresh agent per phase, otherwise continue. A delegated sub-agent gets the plan's path and its phase number and nothing else, since the plan is the brief; it takes the phase through Verify and makes its code commit, and the supervisor writes the ledger row and commits it.

Show full SKILL.md (243 more words)Show less

Nothing in the diff refers to the plan — no code comment, commit message, doc line or release note naming a plan file, a phase, or a plan's numbering. A local plan is gitignored and the code's readers never see either one, so write the reason itself (// storage IDs are stable across a restore), never where it was decided (// per phase 2 of restore-prompt.md).

The ledger

markdown
| Phase | Name | Status | Model / effort | Commit | Notes |
|---|---|---|---|---|---|
| 1 | schema | done | <model> · medium | a1b2c3d | |
| 2 | service and DAO | in progress | <model> · high | | split from phase 1 |

One per plan, and every phase gets its row when the ledger is created — pending, with Model / effort carrying the effort the phase advised, and the model filled in once the phase has run. Status is pending, in progress, done or blocked. Commit is empty until the phase has one, then its SHA (the last, where a phase took several) and/or a #<n> pull request reference; the row lands as its own commit, last in the phase. Notes is a phrase, usually empty.

Below the table, one line each for what a reader would otherwise guess — the set is open:

assumption · storage IDs are stable across restore, per issue comment 4538#12
decision · base is the current HEAD, agreed attended at Workspace
deviation · used the existing modal, not a new page — see a1b2c3d
skip · npm absent, client lint not run
blocked · client lint crashes on pre-existing code; each file this diff touches linted individually

One line per note, never a paragraph, and the whole file stays short. Record where the work stopped and what a resumer could not work out alone, never what was done — point at the commits for that, and a note that will not fit on one line belongs in a commit message. A check that passed needs no line — done claims it; one that failed needs its skip or blocked line even where the phase is otherwise complete.

© epam, 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

Just SKILL.md in .agents/skills/plan-change of epam/cloud-pipeline.

Open the folder on GitHubat commit 5017688

Compare with similar skills

Plan Change 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.

Plan Change compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Plan Change this skillepam/cloud-pipeline162—~1.4kAutomated safety check: PassApache-2.0
Gsd Phaseopen-gsd/gsd-core10k1 repos~603Automated safety check: NotesMIT
Bio Phasing Imputation Haplotype PhasingGPTomics/bioSkills1.2k1 repos~4.2kAutomated safety check: PassMIT
Gsd Execute Phaseopen-gsd/gsd-core10k1 repos~801Automated safety check: NotesMIT
Gsd Spec Phaseopen-gsd/gsd-core10k1 repos~658Automated safety check: NotesMIT
Gsd Mvp Phaseopen-gsd/gsd-core10k1 repos~505Automated safety check: NotesMIT

Similar skills

  • Gsd Phase

    open-gsd/gsd-core

    Multi-phase management — add, insert, remove, or edit phases in ROADMAP.md (roadmap phase CRUD)

    10k GitHub starsUsed in 1 repo~603 tokens
    Product & Project ManagementAuto-check: notes

  • Bio Phasing Imputation Haplotype Phasing

    GPTomics/bioSkills

    Estimates haplotype phase from population linkage disequilibrium with SHAPEIT5, SHAPEIT4, Eagle2, or Beagle - turning unphased genotypes (0/1) into phased haplotypes (0|1) for imputation input…

    1.2k GitHub starsUsed in 1 repo~4.2k tokens
    Research & ScienceAuto-check passed

  • Gsd Execute Phase

    open-gsd/gsd-core

    SDD phase execution — execute all plans in a phase with dependency-aware wave parallelization

    10k GitHub starsUsed in 1 repo~801 tokens
    Agent WorkflowsAuto-check: notes

  • Gsd Spec Phase

    open-gsd/gsd-core

    Clarify WHAT a phase delivers with ambiguity scoring; produces a SPEC.md before discuss-phase.

    10k GitHub starsUsed in 1 repo~658 tokens
    Auto-check: notes

  • Gsd Mvp Phase

    open-gsd/gsd-core

    Plan a phase as a vertical MVP slice — user story, SPIDR splitting, then plan-phase

    10k GitHub starsUsed in 1 repo~505 tokens
    Product & Project ManagementAuto-check: notes

  • Bio Phasing Imputation Haplotype Phasing

    majiayu000/claude-skill-registry

    Phase genotypes into haplotypes using Beagle or SHAPEIT. An agent skill from majiayu000/claude-skill-registry.

    666 GitHub starsUsed in 1 repo~1.1k tokens
    Auto-check passed

More from epam/cloud-pipeline

All 8 skills in this repo

  • Verify Client Live

    epam/cloud-pipeline

    Open a user-visible client/ change in a browser against a real Cloud Pipeline deployment.

    162 GitHub stars~511 tokensUpdated yesterday
    Auto-check passed

  • Configure Dev Environment

    epam/cloud-pipeline

    Learn which toolchains and environments this workstation has and how to invoke them, or set them up when they are missing.

    162 GitHub stars~3.1k tokensUpdated yesterday
    Auto-check passed

  • Commit Changes

    epam/cloud-pipeline

    Required before you commit, push or open a pull request here, asked or not.

    162 GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed

  • Modifying Instructions

    epam/cloud-pipeline

    Required before adding or changing anything an agent reads — a convention in AGENTS.md, a procedure as a skill, a pattern-scoped rule.

    162 GitHub stars~2.2k tokensUpdated yesterday
    Auto-check: warnings

  • Verify Changes

    epam/cloud-pipeline

    Find and run the checks a change owes, from what it touches and what that can reach.

    162 GitHub stars~748 tokensUpdated yesterday
    Auto-check passed

  • Implement Task

    epam/cloud-pipeline

    Start here before the first edit of any file — a one-liner and a docs change included.

    162 GitHub stars~2.9k tokensUpdated yesterday
    Auto-check passed

Questions about Plan Change

What does Plan Change do?

Plan the work before you edit — its phases, the model and effort each takes, and whether it is worth a plan file with a ledger beside it. Plan Change is an agent skill from epam/cloud-pipeline. Plan the work before you edit — its phases, the model and effort each takes, and whether it is worth a plan file with a ledger beside it.

How do I install Plan Change in Claude Code?

Run `npx skills add epam/cloud-pipeline --skill plan-change -a claude-code`. Or copy the skill folder (.agents/skills/plan-change in epam/cloud-pipeline) into .claude/skills/plan-change in your project. Claude Code loads it when a task matches its description.

How do I install Plan Change in Codex?

Run `npx skills add epam/cloud-pipeline --skill plan-change -a codex`. Or copy the skill folder (.agents/skills/plan-change in epam/cloud-pipeline) into .agents/skills/plan-change in your project. Codex loads it when a task matches its description.

Can I use Plan Change 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 epam/cloud-pipeline --skill plan-change -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/plan-change, .gemini/skills/plan-change, .github/skills/plan-change and .opencode/skills/plan-change in your project.

What does Plan Change need to run?

SKILL.md names no scripts, command-line tools or credentials: Plan Change is instructions for the agent only.

Does Plan Change 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 Plan Change 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 Plan Change use?

Plan Change 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 Plan Change use?

About 1.4k tokens (SKILL.md is roughly 5.8k 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 Plan Change?

Skills that share tags, products or a category with Plan Change: Gsd Phase (open-gsd/gsd-core, 10k stars), Bio Phasing Imputation Haplotype Phasing (GPTomics/bioSkills, 1.2k stars), Gsd Execute Phase (open-gsd/gsd-core, 10k stars) and Gsd Spec Phase (open-gsd/gsd-core, 10k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Plan Change?

epam (a GitHub organization) maintains it in epam/cloud-pipeline, which has 162 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on October 6, 2026.

Source: epam/cloud-pipeline on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.