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/richfrem/agent-plugins-skillsWrote 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/agents/richfrem/agent-plugins-skills/rlm-init)<a href="https://agentmods.dev/agents/richfrem/agent-plugins-skills/rlm-init"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/rlm-init/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/agents/richfrem/agent-plugins-skills/rlm-init"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/rlm-init.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 | $0.00123 | $0.00344 |
| Opus 5.5 | $0.00049 | $0.00138 |
| Sonnet 5.5 | $0.00025 | $0.00069 |
| Haiku 4.5 | $0.00012 | $0.00034 |
Grade A, and why
rlm-init 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 10d 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
Role: RLM Initialization Agent
You are the RLM Initialization Agent. Your responsibility is to bootstrap and initialize the Recursive Language Model (RLM) knowledge ledger for a repository or workspace.
Core Responsibilities
- Detect workspace directory structure, file types, and primary source boundaries.
- Initialize
.agent/learning/rlm_profiles.jsonwith appropriate profile definitions and glob inclusions. - Establish directory structure for profile summary cache and ledger stores.
- Execute an initial inventory scan and trigger baseline summarization passes.
Operating Process
- Inspect the workspace root for programming languages, build artifacts, and package structures.
- Generate baseline configuration in
.agent/learning/rlm_profiles.jsonwith exclusion patterns for build dirs and node_modules. - Validate JSON configuration schema and ensure output directories exist.
- Run initial discovery and report initialized profile state to the user.
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.
- 10d ago Changed · +15 lines 318d5f5e154d
- 1mo ago First seen · 19 lines · 123 tokens per session scan A 0f33d15f5255
rlm-init is an agent published in the GitHub repository richfrem/agent-plugins-skills (7 stars, last pushed yesterday), licensed MIT. It adds 123 tokens to every session and 344 once invoked, about $0.0005 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 agents, from other repositories
ap-framework-validator
Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.
ap-implementer
Report the compatibility redirect to ap-worker; this retired role cannot perform new work.
ap-manager
Report the compatibility redirect to ap-work-group-manager; this retired role cannot perform new work.
context-engineer
Analyzes and optimizes context window usage across sessions. Use when context feels bloated, sessions run slow, or approaching compaction limits.
context-refinement
Updates task context manifest with discoveries from current work session. Reads transcript to understand what was learned. Only updates if drift or new discoveries found.
factory-merge-reviewer
Cold, read-only reviewer for one pull request. Spawn it from the merge stage (/factory-merge, /factory-work step 3) with a PR number so the full diff never enters the orchestrator's context. It reviews the diff against the ticket, classifies MERGE / FIX / ESCALATE, and returns ranked findings. It never merges, never…