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/push-learnings)<a href="https://agentmods.dev/commands/closedloop-ai/claude-plugins/push-learnings"><img src="https://agentmods.dev/badge/commands/closedloop-ai/claude-plugins/push-learnings.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 5.1 | $0.00011 | $0.00535 |
| Opus 5 | $0.00005 | $0.00267 |
| Sonnet 5 | $0.00002 | $0.00107 |
| Haiku 4.5 | $0.00001 | $0.00053 |
Grade A, and why
push-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 yesterday.
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
Push Learnings Command
Exports local organization patterns to a shared repository for team-wide distribution.
Prerequisites
CLAUDE_ORG_IDenvironment variable must be set- Git repository must be initialized
- Network access to remote repository
Process
- Read local patterns: Load
$CLOSEDLOOP_WORKDIR/.learnings/org-patterns.toon - Convert TOON → JSON: For cross-project compatibility
- Regenerate pattern IDs: Resolve collisions (P-001 might exist in target)
- Merge with shared patterns: Read
$CLOSEDLOOP_WORKDIR/.closedloop-ai/learnings/org-patterns.json - Track source project: Update
sources.jsonwith origin metadata - Write merged output: Save to shared location
ID Collision Resolution
When merging patterns from multiple projects:
- Load existing IDs from target file
- For each new pattern:
- If ID exists, generate new ID (P-XXX where XXX is next available)
- Preserve original ID in metadata for traceability
Source Tracking
sources.json format:
{
"patterns": {
"P-001": {
"source_project": "project-name",
"source_id": "P-042",
"pushed_at": "ISO8601",
"pushed_by": "[email protected]"
}
}
}
TOON to JSON Conversion
# TOON
P-001|org|pattern|auth_flow|high|5|0.85||impl-subagent,"Check token expiry"
# JSON
{
"id": "P-001",
"scope": "org",
"category": "pattern",
"trigger": "auth_flow",
"confidence": "high",
"seen_count": 5,
"success_rate": 0.85,
"flags": "",
"applies_to": ["impl-subagent"],
"summary": "Check token expiry"
}
Usage
# Requires CLAUDE_ORG_ID to be set
export CLAUDE_ORG_ID="my-organization"
# Then invoke via ClosedLoop orchestrator
Error Handling
- If
CLAUDE_ORG_IDnot set, exit with error - If local patterns file missing, exit with error
- If merge conflict, prefer newer pattern (by timestamp)
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.
- yesterday First seen · 82 lines · 11 tokens per session scan A 075e38f3bf25
push-learnings is a command published in the GitHub repository closedloop-ai/claude-plugins (103 stars, last pushed yesterday), licensed Apache-2.0. It adds 11 tokens to every session and 535 once invoked, about $0.0001 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 2026-09-07.
Other commands, from other repositories
epic-sync
Sync epic issue bodies, labels, and local coordination snapshots from GitHub.
t00-git
A Git assistant that explains version-control commands and guides work with commits, branches, merges, pull requests, and conflicts. Git records code changes so developers can review, restore, and share versions.
t00-publish
A release-preparation command that copies a project into a GitHub staging folder and checks which files are safe to publish.
epic-claim
Claim an epic issue, stamp coordination state, and sync local ownership.
epic-review
Mark epic review requested, approved, or changes requested.
revert
Git-aware undo by logical work unit (track, phase, or task).