Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/star-ga/mind-memnpx agentmods add skills/star-ga/mind-mem/memory-recallWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/star-ga/mind-mem/memory-recall)<a href="https://agentmods.dev/skills/star-ga/mind-mem/memory-recall"><img src="https://agentmods.dev/badge/skills/star-ga/mind-mem/memory-recall.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00567 |
| Opus 5 | $0.00000 | $0.00283 |
| Sonnet 5 | $0.00000 | $0.00113 |
| Haiku 4.5 | $0.00000 | $0.00057 |
Grade A, and why
memory-recall scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- memory-recall — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/recall — Memory Search
Search across all structured memory files. Default backend: BM25 scoring with Porter stemming and domain-aware query expansion. Optional: graph-based cross-reference boosting (--graph). Optional: vector/embedding backend (configure in mind-mem.json). Returns ranked results with block ID, type, score, excerpt, and file path.
When to Use
- Before making decisions (check if a similar decision already exists)
- When asked about past events, decisions, or tasks
- To find related context for a current problem
- To check what's known about a person, project, or tool
- To explore connections between decisions and tasks (
--graph)
How to Run
Basic Search
python3 maintenance/recall.py --query "authentication" --workspace "${MIND_MEM_WORKSPACE:-.}"
Graph-Boosted Search (cross-reference neighbor discovery)
python3 maintenance/recall.py --query "database" --graph --workspace "${MIND_MEM_WORKSPACE:-.}"
JSON Output (for programmatic use)
python3 maintenance/recall.py --query "auth" --workspace "${MIND_MEM_WORKSPACE:-.}" --json --limit 5
Active Items Only
python3 maintenance/recall.py --query "deadline" --workspace "${MIND_MEM_WORKSPACE:-.}" --active-only
What It Searches
decisions/DECISIONS.md— All decisionstasks/TASKS.md— All tasksentities/projects.md— Projectsentities/people.md— Peopleentities/tools.md— Toolsentities/incidents.md— Incidentsintelligence/CONTRADICTIONS.md— Known contradictionsintelligence/DRIFT.md— Drift detectionsintelligence/SIGNALS.md— Captured signals
Scoring
Results are ranked by BM25 relevance (k1=1.2, b=0.75) with:
- Stemming — "queries" matches "query", "deployed" matches "deployment"
- Query expansion — "auth" expands to include "authentication", "login", "oauth", "jwt"
- Recency — Recent items score higher
- Active status — Active items get 1.2x boost
- Priority — P0/P1 items get 1.1x boost
- Graph neighbors — With
--graph, blocks connected via cross-references to keyword matches get a 0.3x boost (tagged[graph]in output)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 53 lines · 0 tokens per session scan A 505c7f683c93
memory-recall is a skill published in the GitHub repository star-ga/mind-mem (15 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 567 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
brain-save
Saves a single fact, decision, pattern, or convention into your governed knowledge brain so it can be recalled later — and retires memories that are outdated. Side-effecting: it writes to your durable corpus, so it never auto-fires — invoke it explicitly. Use when you want the brain to remember something specific…
memoryguard
Local-first MCP memory backend and governance console for coding agents. Auto-organize, quarantine, supersede, and rollback shared memories across multiple agents.
brain
Answers questions about your own systems, notes, decisions, runbooks, and conventions from your governed knowledge brain, returning a qmd:// citation for every claim — receipts, not recall. Use when you want to know what your brain has captured about your own architecture, infrastructure, decisions, or conventions…
memory
Persistent long-term memory via memini. Use to remember durable facts, decisions, and preferences, and to recall relevant context before acting. Triggers when the user says "remember", "what do you know about", or when starting a task that may have prior context.
recall
Search memini for prior context, decisions, or facts relevant to the current task. Use this skill when the user asks "what do you know about X", "did we discuss Y before", or before starting work that may have prior context (a file edit, an architectural change, debugging a recurring issue). The MCP tool is…
recap
Summarize what's known about a project, area, or topic from memini. Use this skill when the user asks "catch me up on X", "what's the state of Y", or "summarize what we know about Z". Builds on recall with a larger limit and tiered grouping. The MCP tool is memoryrecall on the bundled memini server.