capture — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited capture (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Capture a single memory in the moment. Active verb: agent captures the moment of insight, like a photograph.
Call the origin MCP server's capture tool with the user's content as a complete, self-contained statement. Attach topic from cwd or the conversation — don't make the user type it.
capture(content="<args, written as a full sentence with WHY>",
memory_type="<picked from the 6 types>",
entity="<primary entity name, if any>",
space=<inferred>)memory_type — agent picks one of 6The daemon classifies when a local model or API key is configured. In local memory mode it does not, so the agent picks the type from the content itself. Use this mapping:
| Type | Use for |
|---|---|
identity | Durable facts about the user (role, company, language preference) |
preference | "I prefer X because Y" — a habit, a correction, a stylistic choice |
decision | "Going with A over B because C" — a specific choice with rationale |
lesson | Root cause found, workaround discovered, technical insight earned |
gotcha | Sharp edge, surprising behavior, a thing to watch out for |
fact | Durable info about people, projects, tools — anchor to entity when possible |
If two types fit, pick the one closest to why the memory matters. A decision also implies a preference, but decision is more specific.
entity — extract the anchorPick the single most important named thing in the content: a person, project, tool, place. Use the exact name. Example: "Alice prefers TDD because…" → entity="Alice". If the content has no named anchor, omit entity.
topic / space inference~/Repos/origin/... → "origin").space when scope is known; if uncertain, run list_spaceslater (post-PR-C) or omit.
The MCP capture tool takes a single primary entity. For additional entities or relations, use the dedicated MCP tools. If the content names more than one entity, capture the memory first, then for each additional entity:
create_entity(name="<entity>", entity_type="<person|project|tool|place>")For a relation between two entities:
create_relation(from_entity="<a>", to_entity="<b>", relation_type="<verb>")Skip these calls when the daemon has an LLM — its post-ingest enrichment covers extraction.
One capture = one idea. "Prefers TDD" and "Uses pytest" are two captures, not one.
ask required — that's the floor, not the trigger).
/handoff (multi-item batch)./recall.After capture returns, check response.triggered_revisions and response.auto_superseded.
If auto_superseded is non-empty, the daemon already resolved the contradiction. Surface it as informational:
Note: auto-superseded mem_X. Origin replaced a prior protected memory because
trust=high and similarity > 0.9. No action needed.No accept/dismiss call required. The revision was applied automatically.
If triggered_revisions is non-empty (and auto_superseded is empty), render an inline block to the user:
Stored mem_new.
This capture topic-matches a protected memory now flagged for revision:
- mem_target_abc
Action: accept (replace original content) | dismiss (drop the revision) | leave (decide later)Inline verb map:
accept_revision(target_source_id="mem_target_abc")dismiss_revision(target_source_id="mem_target_abc")/briefBoth fields can technically be non-empty in a single response (multiple protected matches), but in practice only one fires per capture: auto_superseded fires when trust=full and similarity > 0.9, triggered_revisions fires otherwise.
If neither field is non-empty, the capture stored cleanly with no conflicts.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.