Menu
When a project-affecting decision has been confirmed in conversation, the main agent invokes this command with the decision context passed as `$ARGUMENTS`.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | ds-memory-update |
| description | When a project-affecting decision has been confirmed in conversation, the main agent invokes this command with the decision context passed as `$ARGUMENTS`. |
| user-invocable | true |
Run the Activation preflight from
METHODOLOGY.mdbefore proceeding. If inactive, no-op and exit.
When a project-affecting decision has been confirmed in conversation, the main agent invokes this command with the decision context passed as $ARGUMENTS.
Immediately spawn a background general-purpose Worker via the Agent tool. Return to the conversation instantly. Do not report completion to the user unless there is an escalation.
Before spawning: The canonical MEMORY.md path is <cwd>/MEMORY.md (loaded at session start via the @MEMORY.md import in the project root CLAUDE.md). Pass this path to the Worker as $MEMORY_PATH.
Orphan data warning: If <cwd>/.agentic/memory/MEMORY.md exists, it was written by a prior buggy version of this command. Its content is NOT auto-injected by Claude Code. Surface this to the operator before spawning:
WARNING: orphaned memory file at .agentic/memory/MEMORY.md detected. Content is not auto-injected. Review manually and merge into <cwd>/MEMORY.md if needed.
Do NOT auto-merge the orphaned file.
What to pass as context: A concise summary of the decision - 1-3 sentences covering what was decided, why, and any key tradeoffs.
When spawning the Worker, substitute $ARGUMENTS with the actual decision context and $MEMORY_PATH with the resolved path before passing the prompt. Do not pass literal placeholder text.
Spawn a background general-purpose Task with this prompt (substitute $ARGUMENTS and $MEMORY_PATH with actual values):
You are a Memory Worker. Your job is to write an accurate, verified entry to MEMORY.md. You will draft, verify, and write in one pass. Do not return a draft for review - write directly to disk.
The decision context: $ARGUMENTS
MEMORY.md path: $MEMORY_PATH
Only proceed if the decision would matter to a new engineer joining the project tomorrow - architectural choices, technology decisions, scope resolutions, deliberate tradeoffs, deferred decisions. Do NOT update MEMORY.md for conversational agreements, personal preferences, or anything that doesn't affect how the project is built or understood. If the decision does not pass this filter, return: "No-op: decision does not qualify for MEMORY.md."
Before drafting, verify any factual claims the entry will make:
# Memory\n\n if it does not exist).- **YYYY-MM-DD:** [what was decided and why, in one sentence with rationale]
# Memory file header.Apply the change directly to the file at $MEMORY_PATH:
# Memory\n\n then write the bulletIf the Worker returned "No-op" or "Abort": complete silently. No further action.
Otherwise: complete silently - do NOT report back to the user.
To query existing memory without rewriting it, use bin/agentic-memory:
# Find recent Skeptic spawns
agentic-memory query --type spawn_complete --agent skeptic --last 5
# Find decisions about a topic
agentic-memory query --source MEMORY.md --topic "context budget"
# Show recent turns
agentic-memory turns --last 5
This is a permitted direct action — the conductor may run it inline without spawning a subagent.
Apply when the user mentions any software development work: implementing features, fixing bugs, reviewing or refactoring code, debugging, testing, deploying, working with agents or subagents, making architecture decisions, setting up projects, managing dependencies, writing scripts, or any task that involves reading, writing, or reasoning about code and systems.
Agentic Engineering Protocol for Hermes - structured delegation model, risk classification, adversarial review loops, code quality gates, git workflow conventions, and named agent definitions. Load this skill when doing AI-assisted software development with Hermes Agent.
Apply when the user mentions any software development work: implementing features, fixing bugs, reviewing or refactoring code, debugging, testing, deploying, working with agents or subagents, making architecture decisions, setting up projects, managing dependencies, writing scripts, or any task that involves reading, writing, or reasoning about code and systems.
Pre-implementation technical design agent. Spawn when you need a structured technical plan before writing code. Reads the codebase, identifies patterns and constraints, evaluates approaches, and produces a concrete plan a Worker can execute directly. Never writes or modifies files.
General-purpose implementation agent. Spawn for any code change: new features, bug fixes, refactors, configuration changes, or script writing. Reads the codebase to understand conventions, implements the change, runs quality gates, and returns a clear summary of what was done. This is the standard Worker for all Elevated-risk implementation tasks.
Cheap per-turn stop-condition check for open-goal loops. Spawned by the conductor ONLY after an Elevated iteration produces a clean Skeptic sign-off, to evaluate the operator-declared goal_condition and return continue-vs-stop only - never for a Low/Trivial iteration (no Skeptic sign-off exists to run after; the conductor evaluates goal_condition directly there instead). Tier 1 (haiku) leaf agent - read-only, no subagent spawning, never runs in place of, before, or concurrently with a Skeptic review. Does NOT review correctness or safety and does NOT raise, waive, or comment on Skeptic findings. Returns BLOCKED only as a structural guard when spawned without a confirmed Skeptic sign-off; the conductor handles this BLOCKED as a fallback to direct evaluation, NOT as the generic Worker-BLOCKED-means-cap_reached-escalation semantics in content/references/subagent-protocol.md - a BLOCKED return here never halts the loop. On any other failure (unavailable, errored, timeout, malformed output) the conductor falls bac