holix-self-diagnose

holix-self-diagnose is a skill for Claude Code from javded-itres/Holix. It costs 59 tokens per session (440 once invoked), scanned A, original, MIT.

A self-diagnosis skill for an AI assistant that runs when the user says the assistant is wrong or asks it to check itself. It reads a diagnostic report before explaining what happened.

In plain words
What is it for?
Use it to investigate incorrect answers, inspect session and tool findings, and report whether a proposed skill fix is live or awaiting approval.
Why use it?
It helps separate actual tool or reasoning failures from unsupported claims and can identify suggested fixes.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions subagents.

Good fit Use it to investigate incorrect answers, inspect session and tool findings, and report whether a proposed skill fix is live or awaiting approval.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/javded-itres/holix/holix-self-diagnose
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 javded-itres/Holix --skill holix-self-diagnose
Clone the repo
git clone --depth 1 https://github.com/javded-itres/Holix

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 holix-self-diagnose

README.md
[![agentmods](https://agentmods.dev/badge/skills/javded-itres/holix/holix-self-diagnose/github.svg)](https://agentmods.dev/skills/javded-itres/holix/holix-self-diagnose)
Your own site
<a href="https://agentmods.dev/skills/javded-itres/holix/holix-self-diagnose"><img src="https://agentmods.dev/badge/skills/javded-itres/holix/holix-self-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.

agentmods 80×15 button for holix-self-diagnose

Your own site · 80×15
<a href="https://agentmods.dev/skills/javded-itres/holix/holix-self-diagnose"><img src="https://agentmods.dev/badge/skills/javded-itres/holix/holix-self-diagnose.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 440 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.
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 $0.00059 $0.00440
Opus 5 $0.00030 $0.00220
Sonnet 5 $0.00012 $0.00088
Haiku 4.5 $0.00006 $0.00044

Measured 2d ago against content hash 575a70664903, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

holix-self-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 2d 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.

core/skills/bundled/holix-self-diagnose/SKILL.md · 45 lines

What it actually says

When to use

The user is criticizing this agent, not asking to debug their own code:

  • «проверь себя», «проверь свою работу», «самодиагностика»
  • «почему ты делаешь не так», «ты отвечаешь неправильно»
  • «check yourself», «you're answering incorrectly»

Procedure

  1. Call self_diagnose immediately (pass their complaint as complaint if useful).
  2. Read findings, plan, session.timeline, session.last_real_ask, failed tools.
  3. Tell the user what went wrong in this session (tools vs claims vs errors). Skills only if a finding is skill_*.
  4. Immediately execute plan.do_now with tools (send file, retry, finish the last ask).
  5. Ask the user only about plan.ask_user (e.g. continue after step limit).
  6. If skill_fixes staged a patch, quote the proposal_id.

Pitfalls

  • Do not answer the complaint from memory. The session transcript is in the tool result.
  • Do not dump or patch unrelated skills. File-delivery skill fix only when the session is about sending files.
  • read_file / cat is not delivering a file. self_diagnose will flag that.
  • Do not auto-spawn sub-agents for this. Main agent only.

Verification

  • This turn has a self_diagnose tool result.
  • The reply quotes findings (code + next_action), not a generic apology.
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. 2d ago Changed · +2 lines 575a70664903
  2. 6d ago First seen · 43 lines · 59 tokens per session scan A 9f1e71208448

Subscribe to this mod's changes

holix-self-diagnose is a skill published in the GitHub repository javded-itres/Holix (14 stars, last pushed 2d ago), licensed MIT. It adds 59 tokens to every session and 440 once invoked, about $0.0003 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 2026-09-04.

Related

Other skills, from other repositories