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 mocasus/paleo --skill paleo-autogit clone --depth 1 https://github.com/mocasus/paleoWrote 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/mocasus/paleo/paleo-auto)<a href="https://agentmods.dev/skills/mocasus/paleo/paleo-auto"><img src="https://agentmods.dev/badge/skills/mocasus/paleo/paleo-auto/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/mocasus/paleo/paleo-auto"><img src="https://agentmods.dev/badge/skills/mocasus/paleo/paleo-auto.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 | $0.00079 | $0.00964 |
| Opus 5 | $0.00039 | $0.00482 |
| Sonnet 5 | $0.00016 | $0.00193 |
| Haiku 4.5 | $0.00008 | $0.00096 |
Grade A, and why
paleo-auto 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.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
paleo-auto
Zero-touch token savings. Enable once, stay on — paleo-auto watches your session and activates the right skills at the right time.
What it does
- Automatic activation. No manual triggers needed. Detects session conditions and enables skills.
- Picks the right combo. Not all skills needed all the time — paleo-auto picks per-condition.
- Safe defaults. Never applies ultra or hard-strict modes unless asked. Always starts at
fullorsoft.
Auto-detection triggers
| Condition | Detection | Action |
|---|---|---|
| Session length >15 turns | Count user/assistant exchanges | Enable paleo (full) + paleo-trim-context |
| Repeated tool output (same tool called 3+ times with similar results) | Compare last 3 tool outputs | Enable paleo-summary (full) |
| Context approaching warning (>60% capacity) | Estimate context usage | Enable paleo-converse (full, N=8) + paleo-trim-context |
| High token cost model detected (GPT-4, Claude Opus, etc.) | Model name check | Enable paleo-budget (soft, 3000 tokens) + paleo (full) |
| Bulky output returned (single tool result >2000 tokens est.) | Output size check | Enable paleo-summary (lite) for subsequent similar calls |
| User sends "long session" / "chatty" / "lagging" | Keyword match | Enable all 7 skills at full defaults |
| Session startup (fresh new session) | First 2 turns | Enable paleo (full) only — low overhead baseline |
Default combo per scenario
| Scenario | Active skills | Why |
|---|---|---|
| Fresh session | paleo (full) |
Low overhead baseline, catches wordy responses |
| Long session | paleo (full) + paleo-trim-context + paleo-converse (N=6) |
Context hygiene + history compression |
| Expensive model | paleo (full) + paleo-budget (soft, 3k) |
Cap costs on pricey models |
| Debugging/tools-heavy | paleo-summary (full) + paleo (full) |
Shrink bulky tool output |
| User says "lagging" / "chatty" | All 7 at full defaults |
Max savings, immediate |
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 · 59 lines · 79 tokens per session scan A 2493196821fb
paleo-auto is a skill published in the GitHub repository mocasus/paleo (20 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 964 once invoked, about $0.0004 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
hermes-context-optimization
Use this when the user asks about Hermes prompt/context size, “hello” startup cost, compression behavior, memory/profile bloat, tool-schema overhead, skill loading, session-store/search-index storage, or multimodal/visual-context approaches such as Snapcompact.
hermes-mnemosyne
Mnemosyne is Hermes' primary local-first memory engine — SQLite with vector + FTS5 hybrid search, 19+ tools, auto-consolidation, and a standalone CLI. It's a pip-installed plugin (not a built-in toolset) discovered via $HERMESHOME/plugins/mnemosyne/.
hermes-session-maintenance
Use this skill when the user asks about pruning Hermes sessions, session retention, session DB size, hermes sessions prune, sessions.autoprune, sessions.retentiondays, session export/backup, or whether old conversations should be capped.
memory-init
Scaffold a project-local memory directory and AGENTS.md guidance for reusable agent knowledge. Use when a user wants to initialize .agents/memories/ or another project memory path so future agents can read and maintain durable project context.
mnemosyne-maintenance
Use when: upgrading Mnemosyne, diagnosing slow/hung consolidation (mnemosynesleep), fixing missing embeddings, or troubleshooting import/version mismatches.
obsidian-memory-architecture
Use when designing, setting up, or maintaining an Obsidian vault as Hermes Agent's durable knowledge layer. Routes facts, conversation history, documents, procedures, and daily logs to the correct Hermes or vault system without duplicating everything into the prompt.