Skill

aidd-rlm

Manages shared RLM evidence workflows for subagents via slice, build, verify, finalize, pack operations using Python scripts. For preload roles requiring consistent RLM handling.

Python

Bash

automation

developer-tools

npx claudepluginhub grinrus/ai_driven_dev --plugin feature-dev-aidd

Configuration

Model: inherit

Tool Access

This skill is limited to using the following tools:

Bash(python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-rlm/runtime/rlm_slice.py *)Bash(python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-rlm/runtime/rlm_nodes_build.py *)Bash(python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-rlm/runtime/rlm_verify.py *)Bash(python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-rlm/runtime/rlm_links_build.py *)Bash(python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-rlm/runtime/rlm_jsonl_compact.py *)Bash(python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-rlm/runtime/rlm_finalize.py *)Bash(python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-rlm/runtime/reports_pack.py *)

Preview

- This skill is preload-only for subagents.

Supporting Assets

runtime/reports_pack.pyruntime/reports_pack_assemble.pyruntime/reports_pack_parts/__init__.pyruntime/reports_pack_parts/core.pyruntime/rlm_finalize.pyruntime/rlm_jsonl_compact.pyruntime/rlm_jsonl_helpers.pyruntime/rlm_links_build.pyruntime/rlm_links_build_parts/core.pyruntime/rlm_links_empty_reason.pyruntime/rlm_nodes_build.pyruntime/rlm_slice.pyruntime/rlm_verify.py

SKILL.md

Similar Skills

loom-ralph

Prepares, launches, and reconciles Ralph implementation packets for bounded features, refactors, tests, migrations, or cleanups on Git-backed Ralph-ready tickets with fresh context, explicit scope, fingerprint, and verification.

7 files

loom

Research Execute Skill

Executes research code in src/ to generate artifacts in results/, reading commands from plan/research_plan.md YAML frontmatter or execution_manifest.json. Phase 3.5 of research pipeline with prerequisite checks.

magi-researchers

rlm

Recursively decomposes and processes large codebases, files, diffs, URLs, and stdin with LLMs for querying, completion, search, and indexing. Triggers on rlm ask/complete/search/index.

rlm

Stats

Stars5

Forks0

Last CommitApr 17, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

Scope

This skill is preload-only for subagents.
Use it to keep RLM behavior consistent across agents without duplicating long instructions.
Preload matrix v2 roles: analyst, planner, plan-reviewer, prd-reviewer, researcher, reviewer, tasklist-refiner, validator.
Do not preload for implementer or qa.

Canonical command paths

Slice (shared): python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-rlm/runtime/rlm_slice.py
RLM runtime entrypoints:
- python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-rlm/runtime/rlm_nodes_build.py
- python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-rlm/runtime/rlm_verify.py
- python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-rlm/runtime/rlm_links_build.py
- python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-rlm/runtime/rlm_jsonl_compact.py
- python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-rlm/runtime/rlm_finalize.py
- python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-rlm/runtime/reports_pack.py

Command contracts

`python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-rlm/runtime/rlm_slice.py`

When to run: when agent needs targeted evidence from existing RLM artifacts without full JSONL scans.
Inputs: --ticket <ticket> with one or more --query tokens.
Outputs: compact slice payload suitable for pack-first reasoning.
Failure mode: non-zero exit when source artifacts are missing or query context is invalid.
Next action: generate/repair missing RLM artifacts, then rerun slice query.

`python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-rlm/runtime/rlm_finalize.py`

When to run: handoff/finalization path when rlm_status remains pending after stage-local bounded recovery.
Inputs: --ticket <ticket> and optional bootstrap/recovery flags.
Outputs: finalized RLM nodes/links/pack status with deterministic readiness metadata.
Failure mode: non-zero exit on unresolved manifest/worklist integrity issues.
Next action: fix upstream targets/worklist inconsistencies and rerun finalize.

Fallback paths

Use canonical Python runtime entrypoints only for new prompts/integrations.

Evidence policy

Read pack-first: aidd/reports/research/<ticket>-rlm.pack.json.
Use slice queries for targeted context extraction.
Avoid full JSONL reads unless pack/slice is insufficient.

Additional resources

Runtime finalize reference: runtime/rlm_finalize.py (when: finalize/handoff behavior is unclear; why: confirm canonical finalize flags and pending/ready transitions).
Cross-skill stage contract: ../aidd-stage-research/SKILL.md (when: researcher stage orchestration and RLM ownership boundary needs clarification; why: keep shared/runtime and stage responsibilities split).