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/mage0535/hermes-memory-installernpx agentmods add skills/mage0535/hermes-memory-installer/memory-proactiveWrote 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/mage0535/hermes-memory-installer/memory-proactive)<a href="https://agentmods.dev/skills/mage0535/hermes-memory-installer/memory-proactive"><img src="https://agentmods.dev/badge/skills/mage0535/hermes-memory-installer/memory-proactive/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mage0535/hermes-memory-installer/memory-proactive"><img src="https://agentmods.dev/badge/skills/mage0535/hermes-memory-installer/memory-proactive.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00014 | $0.00309 |
| Opus 5.5 | $0.00006 | $0.00124 |
| Sonnet 5.5 | $0.00003 | $0.00062 |
| Haiku 4.5 | $0.00001 | $0.00031 |
Grade A, and why
memory-proactive 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 1mo 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.
What it actually says
Memory Proactive
This skill describes the current proactive recall surfaces that remain useful in the local repository.
Layered Context Injection
Primary engine: tiered_context_injector.py
It combines multiple recall paths before the next interaction:
- recent session recall from shared SQLite state
- governance-backed object and hub recall
- knowledge note recall
- optional live Hindsight recall when the query profile needs it
Example:
python3 scripts/tiered_context_injector.py --query "user preferences"
Useful knobs:
--min-score 0.3--max-results 10--recall "project status" "system config"--domains project,stock
Generic Domain Routing
Helper: domain_memory.py
This is a lightweight legacy helper for splitting local memory into generic domains so one topic does not crowd out everything else.
Example domains:
projectstocksystemmarketingrelationshipgeneral
Example:
python3 scripts/domain_memory.py check project "Milestone planning note"
python3 scripts/domain_memory.py status
Guidance
- use generic domains, not user- or project-specific hardcoded labels
- keep recall queries portable across agent runtimes
- treat this skill as an optional helper layer, not a required production contract
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 64 lines · 14 tokens per session scan A 0fd81a349652
memory-proactive is a skill published in the GitHub repository mage0535/hermes-memory-installer (211 stars, last pushed yesterday), licensed MIT. It adds 14 tokens to every session and 309 once invoked, about $0.0001 per session on Opus 5.5. 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
engraphis-memory
Give the agent durable, scoped, explainable memory across sessions and repositories through the Engraphis MCP tools. Use when you learn a convention, decision, bug cause/fix, or user preference worth keeping; when prior context would help before you answer or act (to avoid re-asking or re-deriving); when asked "why is…
ori-memory
Persistent agent memory with learning retrieval. Knowledge graph on markdown files — capture insights, decisions, research, and learnings during work, then retrieve them weeks or months later. Use when knowledge is too valuable to lose but too much to inject into every prompt.
lemmalog
Externalize working memory and logical state into the lemmalog Datalog engine (MCP). Use for ANY multi-step task where state should outlive one context window or span agents: long investigations, debugging sessions, audits, multi-agent searches, systematic explorations, planning with many interdependent constraints…
agent-recall
Persistent compounding memory for AI agents. 5 default MCP tools: sessionstart, sessionend, remember, recall, check. Full surface: 6 tools with --full (adds checkaction); 13 tools with AREXTRAS=1 --full. Two-verb model: inhale (sessionstart) and exhale (sessionend). Correction-first memory with decision trail…
graft
Persistent graph memory shared across conversations and agents. Graft is a prompter, not a cache: it hands you notes that may be close to the problem in front of you, and a close note is already a win - it gives you a starting point and reminds you what was decided before. Search it before non-trivial work, and write…
memory-audit
Maintenance pass + health check of the graft graph. Runs the graft maintain loop: checks what is due, applies the mechanical cleanup, then adjudicates every maintenance candidate (near duplicates, supersessions, contradictions, memories whose source file changed or disappeared, keyword variants, stale low-value notes)…