coplan

coplan is a skill for Claude Code from TechHU-GS/cc-discipline. It costs 35 tokens per session (1,620 once invoked), scanned A, original, MIT.

A command that saves the plan currently being discussed to docs/current-plan.md for review against the real code. It records the proposed path but does not create the plan or implement it.

In plain words
What is it for?
Use it after discussing a plan, such as after a thinking or design step. It helps preserve the current task, approach, and implementation details in one reviewable file before coding begins.
Why use it?
It puts the plan in the project so it can be checked against the actual repository rather than only against the conversation. It also prevents an invented plan from being treated as an agreed one.

Skill for Claude Code

Written for Claude Code: when-to-use in frontmatter. Also seen: mentions Codex.

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/techhu-gs/cc-discipline/coplan
Any agent
npx skills add TechHU-GS/cc-discipline --skill coplan
Clone the repo
git clone --depth 1 https://github.com/TechHU-GS/cc-discipline

Made for: Claude Code.

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 coplan

README.md
[![agentmods](https://agentmods.dev/badge/skills/techhu-gs/cc-discipline/coplan.svg)](https://agentmods.dev/skills/techhu-gs/cc-discipline/coplan)
Your own site
<a href="https://agentmods.dev/skills/techhu-gs/cc-discipline/coplan"><img src="https://agentmods.dev/badge/skills/techhu-gs/cc-discipline/coplan.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,620 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 5.1 $0.00035 $0.01620
Opus 5 $0.00017 $0.00810
Sonnet 5 $0.00007 $0.00324
Haiku 4.5 $0.00003 $0.00162

Measured yesterday against content hash 334b6df4f172, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

coplan 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 yesterday.

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/coplan/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write the plan under discussion to docs/current-plan.md, then stop.

This skill does not produce the plan and does not decide anything. It takes whatever is on the table — the approaches from /think, or a plan just described in conversation — and puts it where a reviewer can read it. Codex runs read-only from the repo root, so a plan on disk is one it can check against the actual code. That is the entire point: a plan pasted into a prompt can only be judged on its own terms, while a plan in the tree can be judged against what is really there.

If there is no plan on the table yet — no approaches from /think, nothing described in conversation — say so and stop. Point at /think instead. Do not invent a plan just to have something to write: a fabricated plan sent for review wastes a review run and produces confident feedback on something nobody proposed. Fabricating content when a skill is invoked is the hardest failure mode to catch in yourself, which makes this the most important line in this file.

The file is a scratch file, not a record

It must not be tracked by git. Before writing, make sure docs/current-plan.md is in .gitignore; add the line if it is missing. If the file is already tracked, say so and offer to untrack it with git rm --cached docs/current-plan.md — do not run that silently, and never commit this file yourself.

  • A tracked file that is always modified becomes a standing passenger. It sits in every git status, so it rides into unrelated commits whenever anything sweeps the working tree. This has already happened: a commit whose message said it touched only documentation also carried temporary debug instrumentation onto main. Untracking removes the passenger; telling someone to be careful does not — /commit already says to stage selectively, and it happened anyway.
  • It is not where the decision lives. What was decided and why belongs in docs/progress.md and in commit messages. Do not create an archive directory for old plans: a third place holding the same facts only guarantees two of them go stale.

Known cost, accepted deliberately: because the file is untracked, hand-edits between revisions no longer show up in git diff, so you lose the view of what you just changed. Self-contradictions have survived several revisions unnoticed for exactly this reason. That cost is smaller than instrumentation reaching main. If a revision matters enough to remember, write the one sentence into progress.md — if you cannot write that sentence, it did not matter.

Read the full file on GitHub · 76 lines

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. yesterday Changed · +30 lines · +5 tokens per session 334b6df4f172
  2. 5d ago First seen · 46 lines · 30 tokens per session scan A 77946c2d14a7

Subscribe to this mod's changes

coplan is a skill published in the GitHub repository TechHU-GS/cc-discipline (0 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 1,620 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

activerecord

This skill should be used when the user asks to "write a migration", "add a column", "add column to table", "create an index", "add a foreign key", "set up associations", "fix N+1 queries", "optimize queries", "add validations", "create callbacks", "use eager loading", or mentions ActiveRecord, belongsto, hasmany…

hoblin/claude-ruby-marketplace · 180 tokens

draper-decorators

This skill should be used when the user asks to "create a decorator", "write a decorator", "move logic into decorator", "clean logic out of the view", "isn't it decorator logic", "test a decorator", or mentions Draper, keeping views clean, or representation logic in decorators. Should also be used when editing…

hoblin/claude-ruby-marketplace · 131 tokens

mcp-server

This skill should be used when the user asks to "create an MCP server", "build MCP tools", "define MCP prompts", "register MCP resources", "implement Model Context Protocol", or mentions the mcp gem, MCP::Server, MCP::Tool, JSON-RPC transport, stdio transport, or streamable HTTP transport. Should also be used when…

hoblin/claude-ruby-marketplace · 98 tokens

ratatui-ruby

This skill should be used when the user asks to "create a TUI", "terminal interface", "terminal UI", "ratatui", "ratatui-ruby", "inline viewport", "full-screen terminal app", "terminal widgets", "tui.draw", "tui.pollevent", or mentions RatatuiRuby.run, managed loop, terminal rendering, Tea MVU, or building CLI…

hoblin/claude-ruby-marketplace · 119 tokens

rspec

This skill should be used when the user asks to "write specs", "create spec", "add RSpec tests", "fix failing spec", or mentions RSpec, describe blocks, it blocks, expect syntax, test doubles, or matchers. Should also be used when editing spec.rb files, working in spec/ directory, planning implementation phases that…

hoblin/claude-ruby-marketplace · 125 tokens

dragonruby

This skill should be used when the user asks to "create a game", "make a game", "game development", "dragonruby", "drgtk", "game loop", "tick method", "sprite rendering", "game state", or mentions args.outputs, args.state, args.inputs, coordinate system, collision detection, animation frames, or scene management.…

hoblin/claude-ruby-marketplace · 100 tokens