harbor-f2p-p2p-deep-dive

harbor-f2p-p2p-deep-dive is a skill for Claude Code from NVIDIA-NeMo/Switchyard. It costs 238 tokens per session (4,997 once invoked), scanned A, original, Apache-2.0.

A guide for investigating Harbor trial results on SWE-Bench-style tasks. Harbor is a task-evaluation system, while SWE-Bench tests coding agents by checking whether they fix reported software issues.

In plain words
What is it for?
Use it to diagnose F2P failures, where required tests still fail, and P2P failures, where previously passing tests were broken.
Why use it?
It separates missing fixes from regressions and checks whether a failed task was genuinely difficult or whether the instructions and tests disagreed.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents; mentions Codex; mentions OpenCode.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 /tests/test_runner.py.

Good fit Use it to diagnose F2P failures, where required tests still fail, and P2P failures, where previously passing tests were broken.

Compare 6 skills from other repositories ↓
About the project

Switchyard is a model-routing library and proxy that chooses which language model should handle each LLM request, based on factors such as cost and task suitability. It is for developers running LLM applications who want to route calls through existing gateways, custom harnesses, or a standalone proxy while retaining OpenAI and Anthropic client compatibility. The catalogue add-ons are workflows for operating or integrating Switchyard with coding agents and gateways.

NVIDIA-NeMo/Switchyard · 2,793 stars · on GitHub

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/NVIDIA-NeMo/Switchyard
agentmods
npx agentmods add skills/nvidia-nemo/switchyard/harbor-f2p-p2p-deep-dive

Made for: Claude Code.

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 harbor-f2p-p2p-deep-dive

README.md
[![agentmods](https://agentmods.dev/badge/skills/nvidia-nemo/switchyard/harbor-f2p-p2p-deep-dive/github.svg)](https://agentmods.dev/skills/nvidia-nemo/switchyard/harbor-f2p-p2p-deep-dive)
Your own site
<a href="https://agentmods.dev/skills/nvidia-nemo/switchyard/harbor-f2p-p2p-deep-dive"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/switchyard/harbor-f2p-p2p-deep-dive/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 harbor-f2p-p2p-deep-dive

Your own site · 80×15
<a href="https://agentmods.dev/skills/nvidia-nemo/switchyard/harbor-f2p-p2p-deep-dive"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/switchyard/harbor-f2p-p2p-deep-dive.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 238 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,997 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 265
    Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.
    Fix: Pin the image: image:tag or image@sha256:abc123
How audits are shown
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 $0.00238 $0.04997
Opus 5 $0.00119 $0.02499
Sonnet 5 $0.00048 $0.00999
Haiku 4.5 $0.00024 $0.00500

Measured 11d ago against content hash 84ab33c43fc2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

harbor-f2p-p2p-deep-dive 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 11d 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.

experimental/craft-taskgen/.claude/skills/harbor-f2p-p2p-deep-dive/SKILL.md · 285 lines

How it starts

The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harbor F2P/P2P Deep Dive

Diagnose why an agent failed a Harbor task whose verifier uses SWE-Bench-style F2P/P2P reference tests. Don't assume a failure mode from the score — split failures by class (F2P vs P2P) and trace each through the actual implementation. Produce a root-cause summary per failing test.

Prerequisites

harbor-lab must be available. From this repo: uv run harbor-lab. From outside the repo: harbor-lab if installed on PATH, otherwise ~/path/to/harbor-lab/.venv/bin/harbor-lab. Set a HLAB shell variable to whichever form works (e.g. HLAB="uv run harbor-lab") and use $HLAB throughout.

Test classes: F2P vs P2P

Harbor verifiers (following SWE-Bench convention) typically split reference tests into two classes:

Class What it is What a failure means
F2P (FAIL_TO_PASS) Tests that fail on the unpatched repo and must pass after the agent's edit Agent didn't implement the requested feature/fix (or implemented it incorrectly)
P2P (PASS_TO_PASS) Tests that pass before and must still pass after Regression — agent broke unrelated existing behavior

A trial is "resolved" only when all F2P pass AND all P2P still pass. The two failure classes have very different diagnostic paths, so split failures by class before triaging:

  • P2P failure → start with regression analysis (the default verdict): the agent touched too much, didn't bound its edits, or its change cascaded. Apply F2P-style validity questions only in narrow cases, all of them rare:
    • Hidden fixture or path dependency the test relies on, never mentioned in the instruction (a reasonable refactor breaks the path).
    • Pre-existing flaky test (timing, network, unseeded randomness) where the agent's change merely shifted execution.
    • Internal-implementation assertion (assert _private_helper() == "old") rather than a public-contract assertion — agent legitimately refactored the private path.
    • Pre-broken test that was passing for unrelated reasons and the agent's edit removed the masking.
    • Instruction wording that forces a change the P2P test catches — agent had no choice (borderline; depends how forcing the wording is).

Read the full file on GitHub · 285 lines

Files

What ships with it

1 file 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. 11d ago First seen · 285 lines · 238 tokens per session scan A 84ab33c43fc2

Subscribe to this mod's changes

harbor-f2p-p2p-deep-dive is a skill published in the GitHub repository NVIDIA-NeMo/Switchyard (2,793 stars, last pushed yesterday), licensed Apache-2.0. It adds 238 tokens to every session and 4,997 once invoked, about $0.0012 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

4-phase root cause debugging: understand bugs before fixing.

NousResearch/hermes-agent · 16 tokens

langsmith-observability

LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.

davila7/claude-code-templates · 45 tokens

experimental-code-coverage-local-debugger

Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.

chromium/chromium · 59 tokens

adversarial-reviewer

Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.

emdash-cms/emdash · 71 tokens

cli-e2e

Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.

ComposioHQ/composio · 62 tokens

work

Deliver one maintainer-approved EmDash issue, choosing the bug-fix path for a defect and the direct implementation path for an enhancement or task.

emdash-cms/emdash · 31 tokens