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.
npx skills add javded-itres/Holix --skill holix-self-diagnosegit clone --depth 1 https://github.com/javded-itres/HolixWrote 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/javded-itres/holix/holix-self-diagnose)<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.
<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>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 | $0.00059 | $0.00440 |
| Opus 5 | $0.00030 | $0.00220 |
| Sonnet 5 | $0.00012 | $0.00088 |
| Haiku 4.5 | $0.00006 | $0.00044 |
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.
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
- Call
self_diagnoseimmediately (pass their complaint ascomplaintif useful). - Read
findings,plan,session.timeline,session.last_real_ask, failed tools. - Tell the user what went wrong in this session (tools vs claims vs errors). Skills only if a finding is
skill_*. - Immediately execute
plan.do_nowwith tools (send file, retry, finish the last ask). - Ask the user only about
plan.ask_user(e.g. continue after step limit). - If
skill_fixesstaged a patch, quote theproposal_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/catis not delivering a file.self_diagnosewill flag that.- Do not auto-spawn sub-agents for this. Main agent only.
Verification
- This turn has a
self_diagnosetool result. - The reply quotes findings (
code+next_action), not a generic apology.
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.
- 2d ago Changed · +2 lines 575a70664903
- 6d ago First seen · 43 lines · 59 tokens per session scan A 9f1e71208448
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.
Other skills, from other repositories
adhoc-verification
Produce fresh, focused, local verification evidence for a code change without relying on the full test suite. Use when a system reminder (or the user) demands ad-hoc verification after an edit, or when you want to prove one behavior in isolation. Covers the correct way to write a throwaway supertest/harness script…
grill-with-docs
Cross-examine codebase architecture against official library documentation and API specs. Identifies deprecations, anti-patterns, and suboptimal library usage.
frontend-visual-verification
Confirm a CSS/HTML/template change actually rendered in a running browser — without being fooled by stale browser cache. Use whenever you edited frontend code (CSS, EJS/HTML, components) and must verify the visual result, especially when a vision screenshot seems to contradict the DOM or the served asset.
node-inspect-debugger
Debug Node.js via --inspect + Chrome DevTools Protocol CLI.
python-debugpy
Debug Python: pdb REPL + debugpy remote (DAP).
hermes-s6-container-supervision
Modify, debug, or extend the s6-overlay supervision tree inside the Hermes Agent Docker image — adding new services, debugging profile gateways, understanding the Architecture B main-program pattern.