OpenClacky is an open-source AI coding agent that uses OpenAI-compatible models to perform tasks through tools and subagents. It is intended for developers who want an agent with flexible model choice and lower token usage. The catalogue skills and agents extend its workflows and capabilities.
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 clacky-ai/openclacky --skill skill-creatorgit clone --depth 1 https://github.com/clacky-ai/openclackyWrote 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/clacky-ai/openclacky/skill-creator)<a href="https://agentmods.dev/skills/clacky-ai/openclacky/skill-creator"><img src="https://agentmods.dev/badge/skills/clacky-ai/openclacky/skill-creator/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/clacky-ai/openclacky/skill-creator"><img src="https://agentmods.dev/badge/skills/clacky-ai/openclacky/skill-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
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 →
- medium Rogue Agent · line 3 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 Excessive Agency · line 59 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Rogue Agent · line 497 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 | $0.00064 | $0.06187 |
| Opus 5 | $0.00032 | $0.03093 |
| Sonnet 5 | $0.00013 | $0.01237 |
| Haiku 4.5 | $0.00006 | $0.00619 |
Grade A, and why
skill-creator scanned grade A with 1 finding 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
task: "Quick mode: create a skill named 'url-summarizer'. It should extract and summarize content from URLs: 1) fetch the URL using terminal with curl, 2) parse the HTML to extract main text content, 3) generate a concis How it starts
The opening of the file, as written. The whole thing — 605 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Creator
A skill for creating new skills and iteratively improving them.
Usage Modes
This skill supports two modes:
1. Interactive Mode (default)
The full workflow with user interviews, test cases, and iteration cycles. Use when creating or refining skills manually.
At a high level, the process of creating a skill goes like this:
- Decide what you want the skill to do and roughly how it should do it
- Write a draft of the skill
- Create a few test prompts and simulate running them (with vs. without the skill instructions)
- Help the user evaluate the results both qualitatively and quantitatively
- While reviewing, draft quantitative assertions if there aren't any
- Use
eval-viewer/generate_review.pyto generate a static HTML viewer for the user to review results and leave feedback
- Rewrite the skill based on the user's feedback
- Repeat until satisfied
Your job is to figure out where the user is in this process and jump in to help them progress through these stages. Maybe they say "I want to make a skill for X" — help narrow down the intent, write a draft, write test cases, evaluate, and repeat. Or maybe they already have a draft — go straight to the eval/iterate part.
Always be flexible. If the user says "skip the evals, just vibe with me", do that instead.
2. Quick Mode (for agent self-evolution)
Trigger: When the task text starts with Quick mode:.
Fast, opinionated skill creation without user interaction. This mode is used by the agent's self-evolution system to automatically create or improve skills.
Behavior:
- Skip user interviews and detailed requirements gathering
- Extract workflow pattern from provided context
- Write a minimal but functional SKILL.md
- Save to
~/.clacky/skills/auto-<name>-<timestamp>/(or improve existing skill in place) - Skip test cases and evals (user can refine later if needed)
- Always validate frontmatter with the validator script after creation
- Focus on the happy path; edge cases can be added later
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/analyzer.md 10 KB
- agents/comparator.md 7.1 KB
- agents/grader.md 8.8 KB
- eval-viewer/generate_review.py 16 KB runs code
- eval-viewer/viewer.html 44 KB
- references/schemas.md 12 KB
- scripts/__init__.py 0 B runs code
- scripts/aggregate_benchmark.py 14 KB runs code
- scripts/generate_report.py 13 KB runs code
- scripts/improve_description.py 13 KB runs code
- scripts/quick_validate.py 3.9 KB runs code
- scripts/run_eval.py 11 KB runs code
- scripts/run_loop.py 13 KB runs code
- scripts/utils.py 1.6 KB runs code
- scripts/validate_skill_frontmatter.rb 4.4 KB runs code
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.
- 10d ago First seen · 605 lines · 64 tokens per session scan A b0c9cc52221e
skill-creator is a skill published in the GitHub repository clacky-ai/openclacky (1,186 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 6,187 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
officecli-word-form
Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trigger on: 'fillable form', 'form fields', 'content controls', 'SDT', 'word form', 'fill in', 'only editable fields', 'protect document'…
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
session-investigator
Investigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debugging tool loops, when correlating sub-agent traces with main sessions, or when analyzing conversation flow and timing. Covers session.json metadata, history JSON format, message structure, tool…
routing-card-authoring
Use whenever a build emits or repairs .agentlas/routing-card.json — the shared card contract for the single-agent builder, the team builder, and the packager. States what belongs in every field, which fields the hub can actually match on, and which fields silently break matching when a sentence leaks into them.
agent-coverage-check
Check agent configuration coverage across hierarchy levels and phases. Use to ensure complete agent system coverage.