Borrowing it
Nothing to install: this file belongs to JNZader/repoforge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/JNZader/repoforge/main/.claude/skills/main/harness/SKILL.mdgit clone --depth 1 https://github.com/JNZader/repoforgeWrote 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/jnzader/repoforge/harness)<a href="https://agentmods.dev/skills/jnzader/repoforge/harness"><img src="https://agentmods.dev/badge/skills/jnzader/repoforge/harness/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/jnzader/repoforge/harness"><img src="https://agentmods.dev/badge/skills/jnzader/repoforge/harness.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 | $0.00034 | $0.00451 |
| Opus 5 | $0.00017 | $0.00226 |
| Sonnet 5 | $0.00007 | $0.00090 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
add-harness-parent-path 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 8d 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.
What it actually says
add-harness-parent-path
This skill covers adding the parent directory to the path when running the harness directly.
Trigger: When using the harness module in a standalone context.
Quick Reference
| Task | Pattern |
|---|---|
| Create FastAPI CRUD module | make_fastapi_crud_module |
| Create Next.js page module | make_nextjs_page_module |
Critical Patterns (Summary)
- Create FastAPI CRUD module: Generates a CRUD module for FastAPI.
- Create Next.js page module: Generates a page module for Next.js.
Critical Patterns (Detailed)
Create FastAPI CRUD module
Generates a CRUD module for FastAPI, allowing for quick API development.
from eval.harness import make_fastapi_crud_module
module = make_fastapi_crud_module("User")
Create Next.js page module
Generates a page module for Next.js, facilitating frontend development.
from eval.harness import make_nextjs_page_module
module = make_nextjs_page_module("HomePage")
When to Use
- When developing a new FastAPI service and needing CRUD operations.
- When creating a new page in a Next.js application.
Commands
python repoforge/cli.py run
Anti-Patterns
Don't: Hardcode paths
Hardcoding paths can lead to issues with portability and maintainability.
# BAD
import sys
sys.path.append('/absolute/path/to/harness')
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.
- 8d ago First seen · 83 lines · 34 tokens per session scan A 5f3ec37f4e64
add-harness-parent-path is a skill published in the GitHub repository JNZader/repoforge (5 stars, last pushed 14d ago), licensed MIT. It adds 34 tokens to every session and 451 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.
Other skills, from other repositories
tmux-manual-qa
Run a single manual tmux-based QA scenario for the todo continuation feature against the real CLI (./pi-test.sh) in an interactive TUI. Captures scrollback, asserts deterministic pass/fail count markers, and cleans up test fixtures. Use only for the manual-qa milestone features.
pi-package-sandbox-test
Use when verifying that published Pi packages install and load for normal users, including pi.dev package compatibility checks, release validation, Daytona sandbox tests, and package installability audits.
agent-eval
Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…
pi-validation-flow
Use when validating Pi monorepo changes after editing TypeScript, Svelte, package manifests, built-in registry, tests, repo tooling, skills, or docs.
eval
Quality and performance evaluation with baseline comparison. Sub-modes: correctness, performance, quality, regression. Outputs PASS/WARN/FAIL per dimension. Use for pre-ship evaluation or regression checks.
go
Go phase. Reads the approved SPEC file, maps Requirements to tasks (plan), executes via TDD (build), and integrates results verifying all Acceptance Criteria.