What is hk-local-diagnose?

A command-line helper for inspecting tasks, specifications, boards, reflections, and saved test snapshots. It selects the matching diagnostic script and output format for the item being checked.

Use it to check a task, spec, board, reflection, or snapshot, with options such as brief, full, JSON, and selected sections.

It removes the need to remember which script, folder, and options belong to each kind of inspection. Short output modes also make diagnostic results easier to review.

hk-local-diagnose — Skill for Claude Code by deepklarity

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/deepklarity/harness-kit

agentmods

npx agentmods add skills/deepklarity/harness-kit/hk-local-diagnose

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/deepklarity/harness-kit/hk-local-diagnose/github.svg)](https://agentmods.dev/skills/deepklarity/harness-kit/hk-local-diagnose)

Your own site

<a href="https://agentmods.dev/skills/deepklarity/harness-kit/hk-local-diagnose"><img src="https://agentmods.dev/badge/skills/deepklarity/harness-kit/hk-local-diagnose/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/deepklarity/harness-kit/hk-local-diagnose"><img src="https://agentmods.dev/badge/skills/deepklarity/harness-kit/hk-local-diagnose.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 893 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.

Model	Per session	Once invoked
Fable 5.1	$0.00113	$0.00893
Opus 5	$0.00056	$0.00447
Sonnet 5	$0.00023	$0.00179
Haiku 4.5	$0.00011	$0.00089

Measured 11d ago against content hash 73330c6532f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

hk-local-diagnose 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.

.claude/skills/hk-local-diagnose/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/hk-local-diagnose — Diagnostic Script Runner

Run the right diagnostic script with the right flags, from the right directory. No more remembering paths or cd-ing around.

Usage

/hk-local-diagnose task 42
/hk-local-diagnose task 42 --brief
/hk-local-diagnose spec 15 --json --sections tasks,problems
/hk-local-diagnose board
/hk-local-diagnose board 3
/hk-local-diagnose reflection 8 --full
/hk-local-diagnose snapshot sp25 ../../tests/e2e_snapshots/smoke

Arguments

Parse $ARGUMENTS to extract:

type (required): task, spec, board, reflection, or snapshot
id (required for all except board): the numeric ID or spec prefix
flags (optional): --brief, --full, --json, --slim, --sections <list>

If no flags are provided, default to --brief — this is the token-efficient choice for LLM consumption. The user can always ask for --full if they need more.

Script mapping

Type	Script	Required args
`task`	`task_inspect.py <id>`	id
`spec`	`spec_trace.py <id>`	id
`board`	`board_overview.py [id]`	id optional
`reflection`	`reflection_inspect.py <id>`	id
`snapshot`	`snapshot_extractor.py <id> <output_dir>`	id + output_dir

Execution

All scripts run from the taskit/taskit-backend/ directory. The working directory for execution is always:

REPO_ROOT/taskit/taskit-backend/

Where REPO_ROOT is the git repository root (find it with git rev-parse --show-toplevel).

Step 1: Resolve the repo root

REPO_ROOT=$(git rev-parse --show-toplevel)

Step 2: Build and run the command

cd "$REPO_ROOT/taskit/taskit-backend" && python testing_tools/<script> <id> [flags]

Pass through any --brief, --full, --json, --slim, or --sections flags directly to the script.

Step 3: Display the output

Print the script output directly. Do not summarize or interpret — the scripts already produce well-structured output with problem detection built in.

Read the full file on GitHub · 90 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.

11d ago First seen · 90 lines · 113 tokens per session scan A 73330c6532f8

Subscribe to this mod's changes

hk-local-diagnose is a skill published in the GitHub repository deepklarity/harness-kit (97 stars, last pushed 1mo ago), licensed MIT. It adds 113 tokens to every session and 893 once invoked, about $0.0006 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.

Debugging agent-skills agentic-ai agentic-framework harness-engineering

neuron-debugger

Debug and monitor Neuron AI applications with Inspector APM, event observability, logging, and performance analysis. Use this skill whenever the user mentions debugging, monitoring, observability, performance analysis, tracing, Inspector, or needs to understand why an agent is behaving a certain way. Also trigger for…

neuron-core/neuron-ai · 90 tokens

diag-harness

Kernel-version skew check (ADR-027). Reports manifest surface + manifest kernel + installed kernel + verdict (match/patch-diff/minor-diff/major-diff). Exits 1 on minor/major skew with a copy-pasteable npm install @metaharness/[email protected] next step. Exits 2 if no .harness/manifest.json at path.

ruvnet/metaharness · 85 tokens

hk-local-diagnose

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/hk-local-diagnose — Diagnostic Script Runner

Usage

Arguments

Script mapping

Execution

Step 1: Resolve the repo root

Step 2: Build and run the command

Step 3: Display the output

What this file has done since we first saw it

Other skills, from other repositories

neuron-debugger

diag-harness

debug-manual

debug-auto

debug

neuron-debugger