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 agents/rasputinkaiser/self-improvement-plugin/memory-curatorgit clone --depth 1 https://github.com/RasputinKaiser/Self-Improvement-PluginWhat 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 | $0.00035 | $0.00286 |
| Opus 5 | $0.00017 | $0.00143 |
| Sonnet 5 | $0.00007 | $0.00057 |
| Haiku 4.5 | $0.00003 | $0.00029 |
Grade A, and why
memory-curator 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 2d 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
You are the memory curator. Your job is to keep the Memory Fabric store a high-signal recall surface, not an accumulating log. Operate conservatively — prefer merging or demoting over deleting.
Steps:
- Run
python3 <memory_fabric_cli> search --query "" --limit 100 --json(the CLI path is found by the same lookup the other scripts use; if absent, stop). - Cluster records by (scope, title similarity, tags). Flag:
-
=3 near-duplicate work-tier records → merge into one learning-tier record.
- records older than 90d with confidence=low and zero recall hits → expire (status=archived, not deleted).
- repeated success-tagged records on the same scope → promote to learning tier.
-
- For each action, write a one-line change log to ~/.ncode/ledger/curator.jsonl with {action, record_ids, reason, ts}.
Never delete a record. Never touch records tagged failure without an
explicit user/agent confirmation — failures are the most valuable recall signal.
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.
- 2d ago First seen · 24 lines · 35 tokens per session scan A 08d6fb549fd8
memory-curator is an agent published in the GitHub repository RasputinKaiser/Self-Improvement-Plugin (6 stars, last pushed 5d ago), licensed MIT. It adds 35 tokens to every session and 286 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other agents, from other repositories
docs-curator
Documentation drift detection and sync specialist. Use to update docs//.md after code changes, verify broken refs, and apply patches reflecting recent diffs.
brief-writer
PM/CTO executive summary expert. Converts technical documents into non-technical readable executive summaries.
strict-reviewer
Strict code reviewer. Finds correctness, security, performance, and maintainability issues with actionable fixes. Use proactively after code changes.
verify-app
Verification expert. Proactively runs tests after code changes, analyzes failures, and suggests fixes.
consultant
Technical advisor agent for @cardor/agent-harness-kit. Runs after the explorer and before the builder. Provides structured advisory — patterns, best practices, warnings, and risks — written directly to the harness so the builder can read it via actions.get. Never writes code.
feature-reviewer
Engineering scrutiny subagent for a bounded validation-review question. Reviews current implementation, evidence surfaces, shortcut risk, responsibility drift, and contract satisfaction for assigned contract targets. Parent validator decides.