harn-probe

harn-probe is a skill for Claude Code from burin-labs/harn. It costs 21 tokens per session (956 once invoked), scanned A, original, Apache-2.0.

A method for checking an uncertain claim in a codebase or running system with the least costly test that could prove it wrong. It helps choose evidence based on whether the claim concerns source code, a contract, behavior, integration, or progress over time.

In plain words
What is it for?
Planning focused code checks, runtime experiments, integration tests, and observations of interruption or recovery when an important claim needs verification.
Why use it?
It reduces the chance of making an expensive decision from an unverified assumption while avoiding unnecessary investigation for facts already settled by reliable evidence.

Skill for Claude Code

Written for Claude Code: when-to-use in frontmatter.

Good fit Planning focused code checks, runtime experiments, integration tests, and observations of interruption or recovery when an important claim needs verification.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/burin-labs/harn/harn-probe
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.

Any agent
npx skills add burin-labs/harn --skill harn-probe
Clone the repo
git clone --depth 1 https://github.com/burin-labs/harn

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 harn-probe

README.md
[![agentmods](https://agentmods.dev/badge/skills/burin-labs/harn/harn-probe/github.svg)](https://agentmods.dev/skills/burin-labs/harn/harn-probe)
Your own site
<a href="https://agentmods.dev/skills/burin-labs/harn/harn-probe"><img src="https://agentmods.dev/badge/skills/burin-labs/harn/harn-probe/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 harn-probe

Your own site · 80×15
<a href="https://agentmods.dev/skills/burin-labs/harn/harn-probe"><img src="https://agentmods.dev/badge/skills/burin-labs/harn/harn-probe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 956 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 pass 7 Sept 2026
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 $0.00021 $0.00956
Opus 5 $0.00010 $0.00478
Sonnet 5 $0.00004 $0.00191
Haiku 4.5 $0.00002 $0.00096

Measured 9d ago against content hash 58da9644bbf5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

harn-probe 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 9d 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.

crates/harn-skills/src/corpus/harn-probe/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harn probe

Use this skill when a material claim is uncertain, temporally unstable, high-risk, or expensive to get wrong. Do not probe by reflex when authoritative source or an existing deterministic check already settles the question.

Pair it with [[harn-testing]] when the probe should become a regression and [[harn-de-slop]] when investigation reveals duplicated ownership.

Frame the claim

  • State the claim precisely.
  • Name the decision the claim affects.
  • Name a plausible falsifier.
  • Estimate the cost of being wrong.
  • Check whether the fact is stable or likely to have changed.
  • Identify the authoritative owner or interface.
  • Stop if the claim is irrelevant to the requested outcome.

Choose evidence by claim type

  • Source claim: inspect the authoritative implementation or registry.
  • Contract claim: inspect the type, schema, protocol, or generated artifact.
  • Deterministic behavior claim: run a focused test through the public interface.
  • Integration claim: exercise the real adapter against a controlled dependency.
  • Product claim: run the canonical path end to end.
  • Liveness claim: observe progress, interruption, recovery, and terminal state.
  • Stochastic quality claim: run multiple trials with a calibrated grader.
  • Performance claim: measure representative distributions and resource ceilings.

Probe design

  • Use the cheapest probe that can distinguish success from failure.
  • Keep one variable changing at a time when possible.
  • Capture inputs, environment, version, and current source identity.
  • Prefer structured output over screenshots or prose.
  • Bound time, concurrency, tokens, and monetary spend.
  • Avoid production effects unless explicitly authorized.
  • Use test adapters for destructive or expensive dependencies.
  • Make the probe repeatable enough to become a regression when useful.

Codebase investigation

  • Start from the repository's authoritative registry or interface.
  • Trace callers only far enough to validate ownership.
  • Search for duplicated policy and parallel implementations.
  • Distinguish generated projections from hand-maintained copies.
  • Inspect blame, issues, or pull requests when intent is not in current source.
  • Check released behavior when source and deployed artifact may differ.
  • Record contradictions rather than smoothing them into one story.
  • Prefer direct evidence to inferred intent.

Read the full file on GitHub · 130 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. 9d ago First seen · 130 lines · 21 tokens per session scan A 58da9644bbf5

Subscribe to this mod's changes

harn-probe is a skill published in the GitHub repository burin-labs/harn (21 stars, last pushed today), licensed Apache-2.0. It adds 21 tokens to every session and 956 once invoked, about $0.0001 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