README

A set of read-only specialist agents that the main Claude Code agent can ask to inspect a project in separate working contexts. Each agent has a limited set of tools and cannot edit files.

In plain words
What is it for?
It helps review plans against project rules and audit security-related concerns before a person approves changes.
Why use it?
It keeps large investigations and focused checks from filling the main agent’s context, while preventing audit agents from changing the code.

Agent 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 agents/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 659 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 $0.00659
Opus 5 $0.00000 $0.00329
Sonnet 5 $0.00000 $0.00132
Haiku 4.5 $0.00000 $0.00066

Measured yesterday against content hash 30278aafbf3f, 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/agents/README.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

.claude/agents/

Sub-agents the main Claude Code agent can delegate to. Each one runs in its own context window, with its own restricted tool set, so the main agent stays focused.

Maps to the talk's framework

Discernimento. Sub-agents are the discernment D — independent, narrow-scope judgement before a human signs off. Read-only by design: they surface what a human should know, never apply fixes.

Why use a sub-agent

The kit's bar for shipping a sub-agent: it has to do something a skill can't. In practice that means either tool restriction (the sub-agent literally can't call Edit / Write) or context isolation for work that would otherwise dump thousands of lines into the main agent's window.

A "specialist who writes blocks" or "specialist who writes REST endpoints" doesn't clear that bar — it's a skill in disguise. So the kit ships exactly two sub-agents, both read-only audits.

Shipped sub-agents

Sub-agent Tools When to invoke
plan-reviewer Read, Grep, Glob, Bash During Phase 2.5 of wordpress-feature, after scripts/open-plan-pr.sh opens the plan PR. Audits spec + plan against PLANNING.md and the constitution.
security-reviewer Read, Grep, Glob, Bash Before merging a feature PR, before a release, after any change to input handling.

Block and REST work is handled by the wp-block-development and wp-rest-api skills the kit pulls from WordPress/agent-skills into .claude/skills/ — those run on the main agent's context, no handoff needed.

How invocation works

Inside Claude Code:

> use the security-reviewer subagent to audit the changes on this branch

The main agent recognizes the sub-agent name, spawns it with its own context, and reports back when it finishes.

Adding your own

  1. Drop a markdown file in this directory.
  2. Frontmatter requires name, description, and tools (comma-separated list).
  3. The body is the sub-agent's system prompt — keep it focused. One job, one playbook.
  4. Reference shared knowledge via @.claude/references/... paths so sub-agents and the main agent share the same source of truth.

Read the full file on GitHub · 50 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 · 50 lines · 0 tokens per session scan A 30278aafbf3f

Subscribe to this mod's changes

README is an agent 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 659 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.

Related

Other agents, from other repositories

test-engineer

Test engineer agent for bug reproduction and verification. Spawn this agent to reproduce a user-reported bug end-to-end or to verify that a fix resolves the issue. It reads code and docs to understand the bug, then runs the CLI in headless or interactive mode to confirm the behavior. It can write test scripts as a…

QwenLM/qwen-code · 119 tokens

diary-writer

generate a diary for user.

QwenLM/qwen-code · 10 tokens

triage-labels

Label vocabulary for triaging/grilling issues in this repository. Managed by smallhours setup — edit .smallhours.yml labels: to rename, then re-run setup; do not edit this file by hand.

bcanfield/agentic-tech-debt · 0 tokens

developer

Implements bounded delivery slices with clear acceptance criteria. TRIGGER when: (1) task has explicit files-to-modify and definition of done, (2) slice is single-role with no architectural uncertainty, (3) the mandatory architect decomposition gate has already been cleared for this task. SKIP: strategic decisions…

yahor-punko/mavericks-os · 0 tokens

architect

Pre-task analysis and architecture design. TRIGGER for all tasks, without exception — mandatory gate before any sub-agent is spawned. Main Agent provides raw task description and codebase context; architect determines task boundaries and returns decomposition. SKIP: implementation, external technology research …

yahor-punko/mavericks-os · 0 tokens

qa

Validates completed slices against acceptance criteria. TRIGGER when: (1) developer marks a slice devdone or readyforqa, (2) runtime or manual verification is required. SKIP: artifact-only or unit-only tasks (validator run / test suite serves as QA), tasks still inprogress.

yahor-punko/mavericks-os · 0 tokens