Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/humanerd-drew/opencode-drewgent/harvester-memory-syncnpx skills add humanerd-drew/opencode-drewgent --skill harvester-memory-syncgit clone --depth 1 https://github.com/humanerd-drew/opencode-drewgentWrote 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/humanerd-drew/opencode-drewgent/harvester-memory-sync)<a href="https://agentmods.dev/skills/humanerd-drew/opencode-drewgent/harvester-memory-sync"><img src="https://agentmods.dev/badge/skills/humanerd-drew/opencode-drewgent/harvester-memory-sync.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 | $0.00000 | $0.00837 |
| Opus 5 | $0.00000 | $0.00418 |
| Sonnet 5 | $0.00000 | $0.00167 |
| Haiku 4.5 | $0.00000 | $0.00084 |
Grade A, and why
harvester-memory-sync 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harvester Memory Sync — P4→P2 Bridge
Purpose
Sync trend-harvester's analyzed trends to P2-hippocampus long-term memory. Keeps P2-hippocampus/memories/insights/ in sync with P4-cortex/growth/trend-harvester/ analyzed output.
This closes the P4→P2 downstream flow: trend-harvester output must reach P2-hippocampus/memories/ so the full memory layer benefits from growth insights.
Trigger
- Primary: Run automatically after trend-harvester-001 job completes
- Fallback: Run on-demand via
python3 scripts/harvester_memory_sync.py
Data Flow
P4-cortex/growth/trend-harvester/
collected/ ← raw data (NOT synced)
analyzed/ ← scored trends → COPY to P2 memories
keep/ ← score ≥ 6.0 → insights/YYYY-MM.md
review/ ← 4.0 ≤ score < 6.0 → insights/pending/
graveyard/ ← NOT synced
pending/ ← approved trends → concepts/
applied/ ← applied trends → concepts/ + notes
P2-hippocampus/memories/
insights/ ← trend insights (by date)
concepts/ ← applied concept files
Sync Rules
| Source (P4) | Destination (P2) | Action |
|---|---|---|
analyzed/keep/*.json |
insights/YYYY-MM.md |
Append to monthly insight |
analyzed/review/*.json |
insights/pending/ |
Create pending insight file |
analyzed/graveyard/*.json |
— | Skip (no sync) |
pending/*.json |
concepts/ |
Create/update concept file |
applied/*.json |
concepts/ |
Create/update concept + tag trend-applied |
Anti-Duplication
- Use content hash (MD5 of trend URL or description) as dedup key
- Check if same hash already exists in target before writing
- Track synced hashes in
{{AGENT_NAME_LOWER}}_hidden_state.json["harvester_synced_hashes"]
State Tracking
Read/write from P4-cortex/knowledge/{{AGENT_NAME_LOWER}}_hidden_state.json:
{
"harvester_synced_hashes": ["hash1", "hash2"],
"last_sync_at": "2026-05-12T10:00:00+09:00",
"last_sync_job": "trend-harvester-001",
"synced_count": 42
}
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.
- 3d ago First seen · 93 lines · 0 tokens per session scan A b0e71eb77431
harvester-memory-sync is a skill published in the GitHub repository humanerd-drew/opencode-drewgent (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 837 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 2026-08-31.
Other skills, from other repositories
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
auditing-subgroup-fairness
Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…