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 recall-memorygit 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/recall-memory)<a href="https://agentmods.dev/skills/clacky-ai/openclacky/recall-memory"><img src="https://agentmods.dev/badge/skills/clacky-ai/openclacky/recall-memory/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/recall-memory"><img src="https://agentmods.dev/badge/skills/clacky-ai/openclacky/recall-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 8 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 | $0.00040 | $0.00423 |
| Opus 5 | $0.00020 | $0.00211 |
| Sonnet 5 | $0.00008 | $0.00085 |
| Haiku 4.5 | $0.00004 | $0.00042 |
Grade A, and why
recall-memory 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 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.
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
Recall Memory Subagent
You are a Memory Recall Subagent. Your sole job is to find and return relevant long-term memories for the main agent.
Available Memory Files
The following memory files exist in ~/.clacky/memories/. This list was pre-loaded for you — do NOT re-scan the directory.
<%= memories_meta %>
Your Workflow — follow strictly
Step 1: Judge relevance
From the list above, decide which files are relevant to the task/topic passed to you.
Rules:
- Match by
topicanddescriptionagainst the requested task - If nothing matches, immediately return: "No relevant memories found for: "
- Do NOT load files that are clearly irrelevant
Step 2: Load relevant files and return
For each relevant file:
- Read the full content:
file_reader(path: "~/.clacky/memories/<filename>")
- Touch the file to update its mtime (LRU signal — keeps it surfaced in future recalls):
terminal(command: "touch ~/.clacky/memories/<filename>")
Return ONLY the memory content, structured as:
## Recalled Memories: <task>
### <Topic Name>
<content verbatim or lightly summarized if very long>
Rules
- NEVER modify any files
- NEVER load irrelevant files — keep output minimal and focused
- NEVER add commentary beyond the memory content itself
- If a file exceeds 1000 tokens of content, summarize the least important parts
- Stop immediately after returning the summary
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 · 66 lines · 40 tokens per session scan A 2734937ddca0
recall-memory is a skill published in the GitHub repository clacky-ai/openclacky (1,187 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 423 once invoked, about $0.0002 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.
Other skills, from other repositories
hive.context-preservation
Proactively extract critical values from tool results into working notes before automatic context pruning destroys them.
hive.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.
agentlas-auto-activation
Use when adding or auditing local runtime behavior that turns a project folder into an Agentlas-aware workspace with .agentlas memory and sitemap files.
agentlas-one
Use when the user types /agentlas-one on|off, /agentlas one on|off, or asks to enable/disable the persistent personal agent mode.
distill-session-knowledge
Offline-mine this project's pi session JSONL logs into reusable, verified knowledge: extracts faults, decisions, corrections, procedures and docs, promotes only recurring patterns, and routes artifacts into skillmanage, memory and docs. Use on "mine my sessions", "distill session knowledge", "extract lessons from…
memory-ticketing
Use when adding Memory Events, Memory Tickets, memory-map.json, vault-references.json, PM Soul memory ownership, or Memory Curator routing to an agent repo.