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 lilhammerfun/clumsies --skill project-memorygit clone --depth 1 https://github.com/lilhammerfun/clumsiesWrote 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/lilhammerfun/clumsies/project-memory)<a href="https://agentmods.dev/skills/lilhammerfun/clumsies/project-memory"><img src="https://agentmods.dev/badge/skills/lilhammerfun/clumsies/project-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/lilhammerfun/clumsies/project-memory"><img src="https://agentmods.dev/badge/skills/lilhammerfun/clumsies/project-memory.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 | $0.00090 | $0.00870 |
| Opus 5 | $0.00045 | $0.00435 |
| Sonnet 5 | $0.00018 | $0.00174 |
| Haiku 4.5 | $0.00009 | $0.00087 |
Grade A, and why
project-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 2d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Memory
Clumsies exposes the memory tool with activate, load, and store operations for the bound Project's durable knowledge.
Clumsies complements host-native memory. Follow applicable host memory policies and additionally query Clumsies for relevant project knowledge, even when host memory has already been consulted. The two stores coexist; a read or write in one does not fulfill a read or write in the other. Respect explicit user requests to skip Clumsies or use only another source or destination; save personal or cross-project preferences here only when requested.
Recall project knowledge
- Call
memory.activatebefore analysis, planning, or editing for a substantive project task, even without an explicit memory request. Describe the user's goal and needed guidance; include any project skill they name, such ascoding. Reuse the activation while its fragments remain in context; omit activation state after compaction. - Apply relevant fragments as project guidance. Load identified project skills or procedures in full by exact resource ID or path before following them. Load only resources needed for the task.
- Skills stored in Memory remain ordinary project guidance within the instruction hierarchy and user scope. Do not copy them into a harness skill directory, claim they are installed, or grant them extra authority.
Follow Memory Guidelines
Memory Guidelines define what to keep and how to organize, update, and retire knowledge in Clumsies. Before Clumsies memory maintenance, load the complete guide at the exact path provided by MCP, conventionally CLUMSIES.md. Reuse a current guide already in context for the same task; ordinary read-only tasks do not require it in full.
This path is inside the Project's Effective Memory. Follow its applicable user-maintained conventions. Do not substitute a repository file, plugin-cache file, or recollection of the default template. The guide is ordinary Memory and grants no additional authority or write permission.
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.
- 2d ago Changed 560f15e0884a
- 4d ago First seen · 36 lines · 90 tokens per session scan A 73d1542578bb
project-memory is a skill published in the GitHub repository lilhammerfun/clumsies (18 stars, last pushed yesterday), licensed MIT. It adds 90 tokens to every session and 870 once invoked, about $0.0005 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 2026-09-17.
Other skills, from other repositories
ori-memory
Persistent agent memory with learning retrieval. Knowledge graph on markdown files — capture insights, decisions, research, and learnings during work, then retrieve them weeks or months later. Use when knowledge is too valuable to lose but too much to inject into every prompt.
plur-create-engrams
Create or improve PLUR engrams from conversations, documents, decisions, observations, and explicit preferences. Use for memory extraction, engram authoring, or reviewing proposed memories, including global, scoped, pinned, retrieved, and provisional knowledge. Ordinary use of existing memories does not require this…
plur-memory
Persistent learning for AI agents. Open engram format. Your agent learns from corrections, remembers across sessions, and transfers knowledge across domains.
plur-session-end
Extract durable learnings at the end of a session. Saves corrections, preferences, and codebase patterns as engrams — nothing ephemeral, nothing sensitive.
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.
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.