abdelmomenmoula/multi-agent-ai-system-for-security-analysis/gsd-mempalace-recall
Claude Code and agent skill by abdelmomenmoula/multi-agent-ai-system-for-security-analysis
- community
Checking that the SKILL.md file is still in the repository.
Recall decisions, patterns, and surprises from MemPalace before planning
Install
npx vskill@latest install abdelmomenmoula/multi-agent-ai-system-for-security-analysis/gsd-mempalace-recallSKILL.md
The same SKILL.md was published earlier as illustriober-creatives/illustriober-cr/gsd-mempalace-recall.
STOP -- DO NOT READ THIS FILE. You are already reading it. This prompt was injected into your context by the command system. Using the Read tool on this file wastes tokens. Begin executing Step 0 immediately.
Step 0 -- Banner
Before ANY tool calls, display this banner:
Then proceed to Step 1.
Step 1 -- Config Gate
Check whether the MemPalace capability is enabled by reading .planning/config.json directly with the Read tool.
DO NOT use `gsd-tools config get-value` -- it hard-exits on missing keys.
- Read
.planning/config.jsonwith the Read tool. - If the file does not exist: write the "unavailable" stub (Step 4) and STOP.
- Parse the JSON. Proceed to Step 2 only if
config.mempalace && config.mempalace.enabled === trueandconfig.mempalace.recall_on_plan !== false. Otherwise display the disabled message and STOP (recall_on_plan: falseturns plan-time recall off while leaving the rest of the capability enabled).
Disabled message:
This step is onError: skip at plan:pre -- recall never blocks planning.
Step 2 -- Resolve wing, mode, and transport
- Wing. Use
config.mempalace.wingif non-empty; otherwise derive fromconfig.project_code; otherwise fall back to the repository directory name. - Mode. Read
config.mempalace.memory_mode(augment|kg_backend|replace, defaultaugment). It sets how authoritative the palace is during recall:
augment— the palace is an additional layer; read native memory (.planning/graphs/, STATE) too and treat the palace as supplementary.kg_backend— for knowledge-graph facts, query the palace's temporal KG first, as the primary source; fall back to.planning/graphs/when the palace is unreachable. Non-KG drawer recall stays additive.replace— resolve recall through the palace as the source of truth; consult native artifacts only as a fallback when the palace is unreachable.
In every mode an unreachable palace degrades to native memory — recall never blocks (onError: skip).
- Transport. Prefer the MCP tools (
mempalace_*) in interactive runs when your MemPalace MCP server is registered and your runtime permits those tools. Otherwise — headless/cron/autonomous runs, or runtimes that don't grant the MemPalace MCP tools — use the CLI (mempalace wake-up,mempalace search), which this skill'sBashallow-tool always covers. If neither is reachable, go to Step 4. - Topic. Read the phase
CONTEXT.md(the consumed artifact). Derive a short search query from its title, goal, and key decisions.
Step 3 -- Retrieve (read-only)
All calls in this step are side-effect-free. On any error or timeout, stop retrieving and write whatever was gathered (or the stub) -- never raise. This skill reads only the palace; GSD's planner reads native memory (.planning/graphs/, STATE) regardless. So under kg_backend/replace an unreachable palace falls back to that native memory automatically — reflect that in the stub (Step 4) rather than implying memory is gone.
- Wake up (cheap, ~600--900 tokens):
- Interactive: read the wing identity/summary, then
mempalace_search. - Headless:
mempalace wake-up --wing <wing>.
- Targeted search:
- Interactive:
mempalace_search(query=<topic>, wing=<wing>). - Headless:
mempalace search "<topic>" --wing <wing>.
- Knowledge-graph facts (when
config.mempalace.mirror_kgis true):mempalace_kg_query/mempalace_kg_timelinefor decisions relevant to the topic and their validity windows. Underaugmentthe palace KG supplements GSD's native.planning/graphs/— combine both, do not treat the palace as the sole source. Underkg_backendorreplacethe palace KG is the primary graph source — query it first and use.planning/graphs/only as a fallback when the palace is unreachable. - Dedup the returned drawers/facts; keep the top results.
Step 4 -- Write MEMORY-RECALL.md
Write MEMORY-RECALL.md in the current phase directory. The planner consumes it.
When recall succeeded, structure it as:
When MemPalace is unreachable, write the stub and continue. Under kg_backend/replace, name the native fallback so the planner knows memory is not gone — only un-augmented by the palace this run:
Anti-Patterns
- DO NOT let any MemPalace error fail the step -- recall is
onError: skip. - DO NOT write to the palace from this skill -- recall is read-only; capture is a separate skill.
- DO NOT paste raw search output into the file -- distil to decisions/patterns/surprises with provenance.
- DO NOT skip the config gate.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingagent/skills/gsd-mempalace-recall/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/abdelmomenmoula/multi-agent-ai-system-for-security-analysis/gsd-mempalace-recall)