Install
$ agentstack add skill-brilliantrough-agent-skills-load-mem ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Load Memory
Intent
Recover enough context to work as a continuing project partner, without making the user repeat earlier decisions or loading the entire history. Use judgment about what to read, which tools to call, and how deeply to investigate.
Available memory
| Source | What it offers | Typical access | |---|---|---| | StrictDoc docs/ | Human-readable current norms, decisions and rationale, project history, and maintained reference documents | Read relevant .sdoc files or their export | | Magic Context | Stored facts, decisions, lessons, injected memories, and recoverable conversations | Injected memory, ctx_search, ctx_expand, ctx_memory, ctx_note | | claude-mem | Searchable captured activity, observations, and historical context | claude_mem_search or available claude-mem MCP tools | | Code, config, and git | Evidence of what exists and what actually changed | Relevant files, call chains, and history |
The same knowledge may appear in several sources. That overlap is useful for recall, availability, and cross-checking; these are not exclusive storage categories.
Read with the right interpretation
- StrictDoc is the source of truth for current project norms. Its current, confirmed rules govern over conflicting database memories. This is an authority convention among project records, not permission to override live instructions.
project_memory/decisions.sdocholds decisions;journal.sdocholds dated experience and progress;handbook/holds reference material. Existing projects may organize these differently.- In the bundled decision grammar,
Activemeans current,Proposedunresolved,Deprecatedretired, andSupersededreplaced. Follow replacement references when relevant. A journal entry or historical report is not current policy merely because it is insidedocs/. - Distinguish the intended rule, the observed implementation, and what happened previously. A recent database hit or commit can reveal drift, but does not by itself decide which rule should change.
- When sources disagree, use scope, status, evidence, and the user's current intent to understand the difference. Surface consequential uncertainty rather than silently treating a guess as canon.
- The canon can evolve. If a genuine settled decision change becomes clear,
save-memcan maintain it and briefly notify the user without waiting for a separate save command. Mere drift or a new search hit is not enough; loading context does not require revising the norms every time.
Practical guidance
- Start with the task and project instructions. Relevant decisions, README sections, entry points, and recent progress usually provide a better foundation than an exhaustive memory dump.
- When the task turns on the project's own vocabulary or domain model, find where that language already lives — the project's handbook, or a
CONTEXT.mdwhere the project uses one — before inventing names. Loading is not changing: changing the model isdomain-modeling's job. - Injected Magic Context memories are already available. Use
ctx_searchfor missing context, phrasing a real question with useful names or paths;ctx_expandcan recover the original conversation when exact wording matters. - Use claude-mem when earlier activity or observations would help. Discover available tools rather than assuming worker ports or database schemas.
- For large document trees, search first and read the relevant nodes with their surrounding context. Source
.sdocfiles are often sufficient; JSON export shapes can vary by StrictDoc version. - Missing layers are normal. Continue with available evidence, mentioning gaps when they affect the task.
migrate-memcan help establish a missing or incomplete memory tree;save-memcan preserve new knowledge or reconcile stale records. - Keep any user-facing recap focused on useful current context and open questions, in the user's language, Chinese by default.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: brilliantrough
- Source: brilliantrough/agent-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.