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.
git clone --depth 1 https://github.com/penfieldlabs/claude-penfieldWrote 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/commands/penfieldlabs/claude-penfield/help)<a href="https://agentmods.dev/commands/penfieldlabs/claude-penfield/help"><img src="https://agentmods.dev/badge/commands/penfieldlabs/claude-penfield/help/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/commands/penfieldlabs/claude-penfield/help"><img src="https://agentmods.dev/badge/commands/penfieldlabs/claude-penfield/help.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 | $0.00007 | $0.00470 |
| Opus 5.5 | $0.00003 | $0.00188 |
| Sonnet 5.5 | $0.00001 | $0.00094 |
| Haiku 4.5 | $0.00001 | $0.00047 |
Grade A, and why
help 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 1mo 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Penfield Memory - Quick Reference
Display this help information to the user:
You Just Talk Naturally
Penfield lets your AI remember things across conversations. You don't need commands - just talk naturally.
Remembering Things
Say things like:
- "Remember this: I prefer morning meetings, not afternoons"
- "Don't forget - Sarah handles legal, John handles IT"
- "Store this decision: We're focusing on enterprise this quarter"
You can tag memories for organization:
- "Remember this and tag it as 'legal': Sarah handles all IP matters"
Recalling Things
Start a new conversation with "Awaken" to load your context, then ask naturally:
- "What did we decide about the pricing strategy?"
- "What do you know about Project Atlas?"
- "What did we discuss last week?"
If your AI doesn't seem to be checking memories, say: "Check your memories first"
Fixing Wrong Information
- "Update memory: I said Sarah handles legal, but actually it's John"
- "Correction - we're NOT focusing on enterprise anymore. Please update."
Connecting Ideas
Usually automatic, but you can be explicit:
- "Connect this decision to our discussion about customer feedback"
- "This contradicts what we thought before - link them"
Project Checkpoints
Save: "Save a checkpoint for Project Alpha - include everything we discussed" Resume: "Restore the checkpoint for Project Alpha"
Artifacts (File Storage)
- "Save this as my standard PR template artifact"
- "Get my PR template artifact"
- "List my saved artifacts"
Exploring Connections
- "Explore connections related to our Q3 strategy"
- "Show me what's connected to Project Atlas"
Key Principles
- Be specific - Include context and reasoning, not just facts
- Correct mistakes immediately - "Update memory: the correct info is..."
- Quality over quantity - Store what matters next week/month/year
Learn More
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.
- 1mo ago First seen · 72 lines · 7 tokens per session scan A 1a613df12bcb
help is a command published in the GitHub repository penfieldlabs/claude-penfield (2 stars, last pushed 8mo ago), licensed MIT. It adds 7 tokens to every session and 470 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-08-31.
Other commands, from other repositories
recall-save
Generate / overwrite .recall/context.md with Recall's local offline summarizer.
show
Show this project's saved Recall context (.recall/context.md).
status
Show memex statistics and status including projects, memos, and pending items.
ccc-context-budget
Show how full the context window is, which components use the most of it, and when to save the session and compact. Use when the session feels slow, long or near its context limit.
tour
Tour this project's memory — what's captured, where it lives, how to recall it (core-memory-kit).
log
Command "log" from allenc84/sapience, covering /log — judgment ledger command, routing, new assessment: /log, review: /log review [domain] and resolve: /log resolve.