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/EntityProcess/allagentsWrote 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/entityprocess/allagents/learn)<a href="https://agentmods.dev/commands/entityprocess/allagents/learn"><img src="https://agentmods.dev/badge/commands/entityprocess/allagents/learn/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/entityprocess/allagents/learn"><img src="https://agentmods.dev/badge/commands/entityprocess/allagents/learn.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 | $0.00015 | $0.00406 |
| Opus 5.5 | $0.00006 | $0.00162 |
| Sonnet 5.5 | $0.00003 | $0.00081 |
| Haiku 4.5 | $0.00002 | $0.00041 |
Grade A, and why
learn 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.
What it actually says
Learn
Extract a learning from the recent conversation and persist it.
Process
-
Identify the problem - Look back through the conversation. Find a mistake, oversight, or suboptimal decision you made. What went wrong?
-
Identify why it was a problem - What was the consequence? Did it cause a bug, require rework, miss an edge case, or violate a convention?
-
Identify the fix - How did the user correct you, or how was it resolved? What was the right approach?
-
Generalize - Can this be stated as a general principle rather than a project-specific fact? Avoid learnings that are too narrow (e.g., "file X is at path Y") — prefer ones that capture reusable judgment (e.g., "when syncing config, only track entries you created").
-
Draft the learning - Write 1-4 sentences that capture the principle. Present this to the user and briefly explain your reasoning.
-
Add it - Append the learning to the
## Learningssection ofCLAUDE.mdin the project root. If no## Learningssection exists, create one at the end of the file.
Format
Each learning is a bullet point, 1-4 sentences:
## Learnings
* When syncing external config files, only track entries you created. Pre-existing user entries must not be tracked, or uninstalling will delete user data.
* CLI output that appears in multiple code paths should use a shared formatter. Adding output to one path but missing others is a common source of inconsistency.
Rules
- One learning per invocation. Keep it focused.
- If no clear mistake happened in the conversation, say so — don't fabricate learnings.
- Always show the draft to the user before writing it to a file.
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 · 39 lines · 15 tokens per session scan A e13b1baec50d
learn is a command published in the GitHub repository EntityProcess/allagents (11 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 406 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
README
Git workflow and quality assurance commands for the claude-skills repository.
cm
Stage working tree changes and create a Conventional Commit (no push).
agent-brain-graph
Search using GraphRAG for relationship and dependency queries.
everme-help
Print a concise EverMe plugin status + reference card.
agent-brain-cache
View embedding cache metrics or clear the cache.
agent-brain-semantic
Search using semantic vector similarity for conceptual queries.