grinrus/aidd-rlm
skills/aidd-rlm/SKILL.md
Owns shared RLM evidence workflow for subagents (slice, build, verify, finalize, pack). Use when preload roles require canonical RLM evidence operations. Do not use when the request is stage-local research execution in `researcher` or stage handoff-only guidance in `aidd-stage-research`.
$ install --global
skillsauthnpx skillsauth add grinrus/ai_driven_dev aidd-rlmInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 22, 2026, 8:05 PM12.8s14 files scanned
SKILL.md
- name:
- aidd-rlm
- description:
- Owns shared RLM evidence workflow for subagents (slice, build, verify, finalize, pack). Use when preload roles require canonical RLM evidence operations. Do not use when the request is stage-local research execution in `researcher` or stage handoff-only guidance in `aidd-stage-research`.
- lang:
- en
- model:
- inherit
- user-invocable:
- false
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
implementerorqa.
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.pypython3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-rlm/runtime/rlm_verify.pypython3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-rlm/runtime/rlm_links_build.pypython3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-rlm/runtime/rlm_jsonl_compact.pypython3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-rlm/runtime/rlm_finalize.pypython3 ${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--querytokens. - 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_statusremains 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).
Related Skills
grinrus/tasks-new
tools
VerifiedTrustedCommunity
Derives or refines tasklist items from PRD and plan artifacts. Use when tasklist stage prepares implementation-ready work items. Do not use when the request is plan authoring in `plan-new` or loop execution in `implement`.
5SKILL.mdUpdated Apr 5, 2026
grinrus/status
testing
VerifiedTrustedCommunity
Generates consolidated ticket status summary and key artifact pointers. Use when checking current stage state or handoff readiness. Do not use when the request is diagnostics/inventory from `aidd-observability` or flow-state mutation via `aidd-flow-state`.
5SKILL.mdUpdated Apr 5, 2026
grinrus/spec-interview
testing
VerifiedTrustedCommunity
Collects missing spec inputs and synchronizes answers into `spec.yaml`. Use when review-spec leaves unresolved specification fields. Do not use when the request is readiness gating in `review-spec` or task derivation in `tasks-new`.
5SKILL.mdUpdated Apr 5, 2026
grinrus/review
testing
VerifiedTrustedCommunity
Runs review-stage validation for scope changes, findings, and follow-up task derivation. Use when review stage needs verdict and handoff tasks. Do not use when the request is direct implementation execution in `implement` or QA validation in `qa`.
5SKILL.mdUpdated Apr 5, 2026