introspect

introspect is a skill for Claude Code from jhlee0409/omni-harness-kit. It costs 104 tokens per session (4,380 once invoked), scanned A, original, MIT.

A repository setup process that examines a project's files and technology choices, then creates tailored guidance and scaffolding for AI coding agents. It can add a concise project guide, stack-specific architect agents, and architecture-decision templates.

In plain words
What is it for?
Use it when setting up agent guidance in a new or existing Git repository, or when updating that guidance after the project's stack changes.
Why use it?
It adapts the general agent workflow to the repository that is actually present, helping agents follow the project's structure and tools without inventing an unsupported technology stack.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the harness-kit plugin — 18 skills, 28 agents, 2 hooks shipped together

Good fit Use it when setting up agent guidance in a new or existing Git repository, or when updating that guidance after the project's stack changes.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add jhlee0409/omni-harness-kit
Claude Code
/plugin install harness-kit

Made for: Claude Code.

Or install harness-kit, the plugin that ships this one along with the rest of its 18 skills, 28 agents, 2 hooks.

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 introspect

README.md
[![agentmods](https://agentmods.dev/badge/skills/jhlee0409/omni-harness-kit/introspect/github.svg)](https://agentmods.dev/skills/jhlee0409/omni-harness-kit/introspect)
Your own site
<a href="https://agentmods.dev/skills/jhlee0409/omni-harness-kit/introspect"><img src="https://agentmods.dev/badge/skills/jhlee0409/omni-harness-kit/introspect/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for introspect

Your own site · 80×15
<a href="https://agentmods.dev/skills/jhlee0409/omni-harness-kit/introspect"><img src="https://agentmods.dev/badge/skills/jhlee0409/omni-harness-kit/introspect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,380 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00104 $0.04380
Opus 5 $0.00052 $0.02190
Sonnet 5 $0.00021 $0.00876
Haiku 4.5 $0.00010 $0.00438

Measured 10d ago against content hash bb8b2ea7f557, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

introspect 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 10d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (aliases.sh, detect.sh, render.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/introspect/SKILL.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

introspect — fit the harness to this repo

You generate the repo-specific layer of the harness. The generic engine (change-verifier and other critic agents, portable skills, the protected-branch guard hook) already ships in the installed harness-kit plugin and fires everywhere — do NOT regenerate or duplicate it. Your job is only what is specific to THIS repository: the CLAUDE.md spine, the stack architect(s), and scaffolding.

Templates live at ${CLAUDE_PLUGIN_ROOT}/templates/. Read them, fill the slots, write the result into the target repo. Never invent a stack you did not observe.

1. Resolve the target

Target dir = the skill argument if given, else the current working directory. Confirm it is a git repo or at least a project root (has a manifest). If a .claude/CLAUDE.md already exists, read it first and treat this as an UPDATE (merge, don't clobber the user's edits) — report what you would change before overwriting.

2. Detect the stack (observe, never assume)

Run a detection sweep and read what you find. Markers and what they imply:

Marker file Implies
package.json Node. Read dependencies/devDependencies + scripts.
pyproject.toml / requirements.txt / setup.py Python.
go.mod Go.
Cargo.toml Rust.
pom.xml / build.gradle JVM.
Gemfile Ruby.
shell test suite (tests/*_test.sh / *.bats) + no other manifest Shell tooling repo (fallback — only when no packaged-language manifest exists).

From package.json dependencies, classify the framework: next→Next.js · react(no next)→React SPA · vue/nuxt→Vue · @modelcontextprotocol/sdk→MCP server · express/fastify/koa→Node API · electron→Electron · none of these + bin→CLI/library. From Python: fastapi/flask/django→web API; mcp→MCP server.

Test runner (from scripts/deps): vitest · jest · mocha · pytest · go test · cargo test. Capture the actual command (prefer the repo's own test script, e.g. npm test).

Read the full file on GitHub · 278 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 278 lines · 104 tokens per session scan A bb8b2ea7f557

Subscribe to this mod's changes

introspect is a skill published in the GitHub repository jhlee0409/omni-harness-kit (2 stars, last pushed 1mo ago), licensed MIT. It adds 104 tokens to every session and 4,380 once invoked, about $0.0005 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

resolve-plugins

Curate Claude Code skill / MCP / hook picks against live upstream sources and pin them in .claude/settings.json. Adding a process harness (a paired skill set) is an ordinary pick this door handles. Reads stack from docs/techstack.md, workflow signal from docs/overview.md + existing pins, then live-queries six source…

RockyHong/super-bootstrap · 133 tokens

journey-simulation

Use when caller wants to observe how a stranger encounters a flow, artifact, or sandbox — triggers like "simulate a user journey", "test our onboarding / checkout / signup", "will my ICP convert", "how does a cold reader experience this README", "first-time user test", "cognitive walkthrough", or any request to…

RockyHong/super-bootstrap · 79 tokens

check-docs-consistency

Cross-reference project docs for drift, stale references, and contradictions. Outputs timestamped report. Discovers Markdown wherever it lives in the repo.

RockyHong/super-bootstrap · 34 tokens

super-bootstrap

Public entry for the super-bootstrap pipeline — thin orchestrator. Git-inits if absent, then dispatches /super-bootstrap:harness-bootstrap to install or sync the generic runway (always; the runway self-detects fresh-vs-sync). Checks whether seed docs are substantive: greenfield seeds three GAP cards (overview…

RockyHong/super-bootstrap · 115 tokens

release

Prepare a version release — bump version files, commit, and tag. Just run /release with no arguments.

RockyHong/super-bootstrap · 24 tokens

merge

Absorb one or more feature branches into the base branch. Recommends merge vs rebase per branch. On conflict, aborts that branch + surfaces the file list + stops. Resolution out of scope; routes to the harness-named conflict-resolution agent or the user.

RockyHong/super-bootstrap · 57 tokens