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 agentmods add skills/phasespace-labs/palinode/palinode-claude-codenpx skills add phasespace-labs/palinode --skill palinode-claude-codegit clone --depth 1 https://github.com/phasespace-labs/palinodeWrote 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/phasespace-labs/palinode/palinode-claude-code)<a href="https://agentmods.dev/skills/phasespace-labs/palinode/palinode-claude-code"><img src="https://agentmods.dev/badge/skills/phasespace-labs/palinode/palinode-claude-code.svg" alt="Measured on agentmods" 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 | $0.00147 | $0.00878 |
| Opus 5 | $0.00073 | $0.00439 |
| Sonnet 5 | $0.00029 | $0.00176 |
| Haiku 4.5 | $0.00015 | $0.00088 |
Grade A, and why
palinode-claude-code 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 4d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Palinode — Claude Code Integration
Palinode gives Claude Code persistent, git-versioned memory via 13 MCP tools. Memories survive across sessions, are searchable by meaning, and consolidate weekly.
Session Workflow
Before Starting Work
Use palinode_search to find any prior context on [project/topic]
Surfaces relevant decisions, people context, and insights automatically.
During Work — Save Key Decisions
When you make an architectural or product decision:
palinode_save: decided to [X] because [Y]. trade-off was [Z].
type: Decision
entities: [project/name]
After a Long Session
Save key decisions and insights from this session to palinode
Core Tools Quick Reference
| Tool | Call Pattern |
|---|---|
| Search | palinode_search(query="...", limit=5) |
| Save decision | palinode_save(content="...", type="Decision", entities=["project/name"]) |
| Save insight | palinode_save(content="...", type="Insight") |
| Save person | palinode_save(content="...", type="PersonMemory", entities=["person/name"]) |
| Status | palinode_status() |
| Recent changes | palinode_diff(file="projects/name.md", n_commits=3) |
| Register trigger | palinode_trigger(action="add", description="...", memory_file="path/to/file.md") |
| Consolidate | palinode_consolidate(dry_run=True) |
Memory Types
Decision— what was decided and why (rationale is critical)Insight— generalizable lessons (applies beyond one project)PersonMemory— person's role, preferences, constraintsProjectSnapshot— current state (milestones, blockers, next steps)ActionItem— follow-up with owner and deadline
When to Save vs. Not
Save:
- Architectural decisions with rationale
- Bugs that took >30min to find (so future-you recognizes them)
- Performance findings (e.g., "bge-m3 cold start is 30s, warm is 100ms")
- People context (preferences, constraints, relationships)
- Lessons that apply broadly across projects
Don't save:
- Raw code (git handles it)
- Step-by-step log of what you did (save the outcome, not the journey)
- Temporary debug notes
What ships with it
1 file 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.
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.
- 4d ago First seen · 96 lines · 147 tokens per session scan A 4a634c413e21
palinode-claude-code is a skill published in the GitHub repository phasespace-labs/palinode (35 stars, last pushed today), licensed MIT. It adds 147 tokens to every session and 878 once invoked, about $0.0007 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
kayba-ace
This skill ships learnfromtraces.py, a script that reads OpenClaw session transcripts, feeds them through the ACE learning pipeline, and writes an updated skillbook to disk.
plur-memory
Persistent learning for AI agents. Open engram format. Your agent learns from corrections, remembers across sessions, and transfers knowledge across domains.
plur-memory
Your memory stays on your machine. No cloud, no tracking, no API key. PLUR makes your OpenClaw remember — and shares that memory with every other tool you use.
lemmalog
Externalize working memory and logical state into the lemmalog Datalog engine (MCP). Use for ANY multi-step task where state should outlive one context window or span agents: long investigations, debugging sessions, audits, multi-agent searches, systematic explorations, planning with many interdependent constraints…
honcho-integration
Integrate Honcho memory into existing Python or TypeScript codebases. Use when adding Honcho SDK, setting up peers, configuring sessions, and accessing Honcho's representation.
honcho-memory
Concepts and strategy for using a connected Honcho as persistent memory of the user — the recall/record loop and session and peer design. Start here to understand how Honcho memory works, then connect — via a first-class integration for your environment if one exists (preferred), or raw MCP tools (covered here) or the…