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/closedloop-ai/claude-pluginsWrote 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/closedloop-ai/claude-plugins/export-closedloop-learnings)<a href="https://agentmods.dev/commands/closedloop-ai/claude-plugins/export-closedloop-learnings"><img src="https://agentmods.dev/badge/commands/closedloop-ai/claude-plugins/export-closedloop-learnings/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/closedloop-ai/claude-plugins/export-closedloop-learnings"><img src="https://agentmods.dev/badge/commands/closedloop-ai/claude-plugins/export-closedloop-learnings.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 | $0.00013 | $0.00851 |
| Opus 5.5 | $0.00005 | $0.00340 |
| Sonnet 5.5 | $0.00003 | $0.00170 |
| Haiku 4.5 | $0.00001 | $0.00085 |
Grade A, and why
export-closedloop-learnings 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 8d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Export ClosedLoop Learnings Command
Merges ClosedLoop-specific learnings from the current project into a global learnings store at ~/.closedloop-ai/learnings/closedloop-learnings.json with automatic deduplication.
Purpose
When learnings are captured that improve ClosedLoop itself (agents, workflows, hooks), they should be automatically exported to a global location where they persist across projects. This command handles deduplication to prevent redundant entries.
Process
- Read pending closedloop learnings: Load
$CLOSEDLOOP_WORKDIR/.learnings/pending-closedloop.json - Read existing global learnings: Load
~/.closedloop-ai/learnings/closedloop-learnings.json(create if missing) - Deduplicate: For each pending learning:
- If exact
triggermatch exists → skip (already exists) - If 80%+ word overlap on
summary→ skip (duplicate) - Otherwise → add as new learning with unique ID
- If exact
- Merge and write: Append non-duplicate learnings with
merged_attimestamp - Clear pending: Remove
pending-closedloop.jsonafter successful merge
Input Format
pending-closedloop.json:
{
"learnings": [
{
"id": "L-001",
"scope": "closedloop",
"category": "pattern",
"trigger": "plan-writer error handling",
"summary": "Plan-writer should validate task dependencies before writing",
"detail": "Found that missing dependency validation causes plan failures",
"source_project": "my-project",
"captured_at": "ISO8601"
}
]
}
Output Format
Global file at ~/.closedloop-ai/learnings/closedloop-learnings.json:
{
"schema_version": "1.0",
"last_updated": "ISO8601",
"learnings": [
{
"id": "SL-001",
"trigger": "plan-writer error handling",
"summary": "Plan-writer should validate task dependencies before writing",
"detail": "Found that missing dependency validation causes plan failures",
"category": "pattern",
"source_project": "my-project",
"captured_at": "ISO8601",
"merged_at": "ISO8601"
}
]
}
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.
- 8d ago Changed · -1 lines 0f750bcb525b
- 1mo ago First seen · 96 lines · 13 tokens per session scan A 8396abf80a52
export-closedloop-learnings is a command published in the GitHub repository closedloop-ai/claude-plugins (123 stars, last pushed today), licensed Apache-2.0. It adds 13 tokens to every session and 851 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 2026-09-07.
Other commands, from other repositories
instinct-import
Import instincts from external sources.
learn
Extract patterns and learnings from current session.
context-restore
Restore saved project context and decisions to resume a session.
context-save
Save project context, decisions, and progress for a later session.
help
Get help with EverMem plugin setup and available commands.
ingest
Ingest source material into an active wiki. Accepts URLs, file paths, PDFs, freeform text, or processes the inbox. Supports tweets via Grok MCP.