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-extensionsgit 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-extensions)<a href="https://agentmods.dev/skills/javded-itres/holix/holix-extensions"><img src="https://agentmods.dev/badge/skills/javded-itres/holix/holix-extensions/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-extensions"><img src="https://agentmods.dev/badge/skills/javded-itres/holix/holix-extensions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
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 →
- high Rogue Agent · line 6 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- medium Rogue Agent · line 43 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 74 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00066 | $0.01597 |
| Opus 5.5 | $0.00026 | $0.00639 |
| Sonnet 5.5 | $0.00013 | $0.00319 |
| Haiku 4.5 | $0.00007 | $0.00160 |
Grade A, and why
holix-extensions 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use
The user wants the agent to grow new capabilities safely:
- add a custom tool or slash command
- “напиши расширение”, “допиши себя”, “добавь skill/tool”
- list what extensions are loaded
- disable something that breaks the agent
Never edit Holix core (core/, cli/, integrations/, package source).
Only create profile-local drop-in extensions.
Who may change extensions (important)
create / enable / disable / reload / settings_get / settings_set are operator actions:
| Actor | Allowed |
|---|---|
CLI, TUI, holix run |
Yes (local operator) |
| Telegram / MAX bot admin | Yes |
| Telegram / MAX regular user | No (self_extensions_denied) |
Regular users may only list and registered.
Override (not for shared bots): HOLIX_SELF_EXTENSIONS=1. If denied, tell a non-admin to ask the bot admin — do not try to bypass.
Architecture (safe zone)
~/.holix/profiles/<profile>/extensions/<name>/
agent.py # get_agent_extension()
holix.plugin.json
settings.default.yaml
README.md
- Discovered on agent start and via hot-reload after
create/reload(local mode). - Does not require pip install.
- Same profile only (unless user copies to
~/.holix/extensions/).
Primary tool
Use manage_agent_extensions:
| action | Purpose | Local only? |
|---|---|---|
list |
Folders + blocked status | No |
registered |
Settings + slash commands | No |
create |
Scaffold + hot-reload into this session | Yes |
disable |
Kill-switch; hot-unload when local | Prefer anytime |
enable |
Re-enable + hot-reload | Yes |
quarantine_clear |
Clear auto-quarantine + reload | Yes |
reload |
Re-scan extensions / reimport modules | Yes |
show_control |
Show agent_extensions_control.yaml |
Operator |
settings_get |
Read extension_settings/<name>.yaml |
Operator |
settings_set |
Merge JSON into extension settings + reload | Operator |
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.
- 1mo ago Changed · +3 lines bd90f19862ab
- 2mo ago First seen · 204 lines · 66 tokens per session scan A 7e74ef02bad4
holix-extensions is a skill published in the GitHub repository javded-itres/Holix (20 stars, last pushed 11d ago), licensed MIT. It adds 66 tokens to every session and 1,597 once invoked, about $0.0003 per session on Opus 5.5. 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.
holix-extensions compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| holix-extensionsjavded-itres/Holix | Skill | 20 | 11d ago | MIT | A | 66 | Claude Code |
| a0-developmentagent0ai/agent-zero | Skill | 20k | yesterday | none | A | 24 | Claude Code, Codex |
| a0-developmentGen-Verse/PAST-Bench | Skill | 37 | 3mo ago | Apache-2.0 | C | 52 | Claude Code, Codex |
| agent-creationstencila/stencila | Skill | 916 | 2d ago | Apache-2.0 | A | 53 | Claude Code |
| yida-create-form-pageopenyida/openyida | Skill | 233 | yesterday | MIT | A | 54 | Claude Code, Codex |
| yida-custom-pageopenyida/openyida | Skill | 233 | yesterday | MIT | A | 67 | Claude Code, Codex |
| yida-canvas-data-bindingopenyida/openyida | Skill | 233 | yesterday | MIT | A | 104 | Claude Code, Codex |