setup

A setup command for connecting the self-improvement plugin’s agents, commands, review hooks, and supporting scripts after installation or an update.

In plain words
What is it for?
It helps install the plugin’s links and scripts, add its session review hook, update the agent instructions, and check the prerequisite for background Pushover summaries.
Why use it?
It removes the need to create and check each plugin connection by hand, while also reporting if the plugin is not installed.

Command

Install

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.

agentmods
npx agentmods add commands/trtmn/agent-plugins/setup
Clone the repo
git clone --depth 1 https://github.com/trtmn/agent-plugins
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 313 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00313
Opus 5 $0.00000 $0.00156
Sonnet 5 $0.00000 $0.00063
Haiku 4.5 $0.00000 $0.00031

Measured yesterday against content hash 8d8b0cfe111e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

setup scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- Merges the gated `SessionEnd` review hook into `~/.claude/settings.json`.
plugins/self-improvement/commands/setup.md · 15 lines

What it actually says

Wire up the self-improvement plugin (capture + autonomous review) after installation or update.

  1. Read ~/.claude/plugins/installed_plugins.json and find the installPath for self-improvement@agent-plugins.
  2. Run bash <installPath>/scripts/setup.sh and show the output.
  3. If the plugin isn't installed, tell the user to run /plugin install self-improvement@agent-plugins first.

The setup script is idempotent. It:

  • Symlinks the learnings, self-improvement, and learning-investigator agents into ~/.claude/agents/ (force-overwriting any stale learnings.md link from the old standalone plugin, and verifying each link resolves).
  • Symlinks the /self-improvement and /self-improvement:revert commands into ~/.claude/commands/.
  • Deploys review-trigger.sh, pending-count.sh, and revert.sh to ~/.claude/self-improvement/.
  • Merges the gated SessionEnd review hook into ~/.claude/settings.json.
  • Patches ~/.claude/CLAUDE.md (passive-logging delegation + autonomous-review note).

After running, note the prerequisite it prints: for the Pushover summary to fire from the autonomous run, OP_SERVICE_ACCOUNT_TOKEN must be reachable by background processes (exported in your shell profile, or in the file the trigger reads).

Changes

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.

  1. yesterday First seen · 15 lines · 0 tokens per session scan B 8d8b0cfe111e

Subscribe to this mod's changes

setup is a command published in the GitHub repository trtmn/agent-plugins (2 stars, last pushed 4d ago), licensed Unlicense. It costs nothing until one of its globs matches a file; then it loads 313 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.