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.
/plugin marketplace add jhlee0409/omni-harness-kit/plugin install harness-kitWrote 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.
[](https://agentmods.dev/skills/jhlee0409/omni-harness-kit/introspect)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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.
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).
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.
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.
- 10d ago First seen · 278 lines · 104 tokens per session scan A bb8b2ea7f557
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.
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…
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…
check-docs-consistency
Cross-reference project docs for drift, stale references, and contradictions. Outputs timestamped report. Discovers Markdown wherever it lives in the repo.
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…
release
Prepare a version release — bump version files, commit, and tag. Just run /release with no arguments.
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.