README

A set of project-specific slash commands for Claude Code, a coding assistant that works in your terminal. Each command turns a short `/name` entry into a fixed sequence of instructions or project actions.

In plain words
What is it for?
Use `/plan-freeze` to commit a feature plan, push a branch, and open a pull request; `/audit-plan` to run a read-only plan review; and `/ship-feature` to mark a merged feature complete and archive its files.
Why use it?
It removes the need to repeat routine instructions and remember the exact steps for common project tasks. It also helps keep planning, review, and shipping actions consistent.

Command for Claude Code

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 commands/pluginslab/wp-agentic-kit/readme
Clone the repo
git clone --depth 1 https://github.com/pluginslab/wp-agentic-kit

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 470 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 $0.00000 $0.00470
Opus 5 $0.00000 $0.00235
Sonnet 5 $0.00000 $0.00094
Haiku 4.5 $0.00000 $0.00047

Measured yesterday against content hash 5a939447b1ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

README 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/commands/README.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

.claude/commands/

Project-scoped slash commands. Type /<name> in a Claude Code session and the command's body becomes the agent's marching orders for that turn.

Shipped commands

Command What it does
/plan-freeze [slug] Commits the active feature's spec.md + plan.md, pushes a plan/ branch, opens a PR. Wraps scripts/open-plan-pr.sh.
/audit-plan [slug] Dispatches the plan-reviewer sub-agent against the active feature's plan. Read-only audit.
/ship-feature [slug] After the feature PR merges: marks progress.md complete and moves the dir to .claude/plans/archive/.

Each command auto-detects the active feature when called without an argument (most recently modified progress.md whose status isn't a completion synonym).

Why slash commands, not skills

Skills are interview-driven workflows (multi-phase, branching). Commands are one-step shortcuts. Use a command when the work is "always do exactly this sequence."

The three above wrap three different primitives:

  • plan-freeze → a shell script (open-plan-pr.sh)
  • audit-plan → a sub-agent (plan-reviewer)
  • ship-feature → file-system + git operations

Without the commands you'd type the script invocation, the sub-agent dispatch, or the archive sequence from memory each time. The commands move that into muscle memory — /plan-freeze is shorter than ./scripts/open-plan-pr.sh 003-order-status-block.

Frontmatter

---
description: One sentence shown in the slash command picker.
argument-hint: "[feature-slug]"
---

Both fields are optional but recommended. $ARGUMENTS in the body substitutes whatever the user typed after the command name.

Adding a command

  1. Drop a <name>.md in this directory.
  2. Add the frontmatter.
  3. Write the body as instructions to the agent — verbs in second person, one step per line.
  4. If the command needs new tools or scripts, register them in .claude/settings.json so the agent doesn't ask permission every time.

Read the full file on GitHub · 44 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 First seen · 44 lines · 0 tokens per session scan A 5a939447b1ac

Subscribe to this mod's changes

README is a command published in the GitHub repository pluginslab/wp-agentic-kit (18 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 470 tokens. 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.