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 skills add Ertinox7711/SGRR-AGI-V2 --skill refinegit clone --depth 1 https://github.com/Ertinox7711/SGRR-AGI-V2Wrote 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/ertinox7711/sgrr-agi-v2/refine)<a href="https://agentmods.dev/skills/ertinox7711/sgrr-agi-v2/refine"><img src="https://agentmods.dev/badge/skills/ertinox7711/sgrr-agi-v2/refine/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/ertinox7711/sgrr-agi-v2/refine"><img src="https://agentmods.dev/badge/skills/ertinox7711/sgrr-agi-v2/refine.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00131 | $0.01622 |
| Opus 5.5 | $0.00052 | $0.00649 |
| Sonnet 5.5 | $0.00026 | $0.00324 |
| Haiku 4.5 | $0.00013 | $0.00162 |
Grade A, and why
refine 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 23d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refine - Continual Harness
Port of PrimeIntellect prime-agent's Continual Harness (/refine, MIT,
https://github.com/PrimeIntellect-ai/prime-agent) onto this rig.
Refinement reads the current trajectory and applies small, evidence-backed edits to durable rig state. It is compaction's sibling: compaction summarizes the conversation, refinement extracts what should outlive it.
The base ~/.claude/CLAUDE.md is IMMUTABLE. Refinement never rewrites it.
The four kinds
| kind | what it is | where it lands on this rig |
|---|---|---|
prompt |
narrow behavioral policy addendum | harness/addendum/PROMPT-NOTES.md, injected at SessionStart |
memory |
durable fact, decision, failure, preference, outcome | ~/.claude/projects/<enc>/memory/<slug>.md + MEMORY.md line |
skill |
repeatable procedure worth invoking by name | ~/.claude/skills/<name>/SKILL.md |
subagent |
reusable delegation role | ~/.claude/agents/<name>.md |
Create or update the smallest component that fits. Repeated delegation role -> subagent. Repeated procedure -> skill. Durable fact or preference -> memory. Narrow behavioral policy -> prompt note. Do not rewrite the whole harness when a focused entry is enough.
Scope
--scope global(default): stable cross-session lessons, durable user preferences, reusable skills/subagents, tool or environment facts. Store:~/.claude/harness/.--scope local: session/project-specific progress, active task state, temporary blockers, project facts that must not leak into other sessions. Store:<project>/.claude/harness/.
A project-specific lesson may go global only when its title or content explicitly names the project and it will be reused in future sessions for that project. Otherwise: local.
Hard rule on this rig - no removal
The operator's standing rule (the no-removal rule) overrides the upstream design:
action: "create"andaction: "update"are free.action: "delete"is REFUSED by the engine unless--allow-deleteis passed, and that flag is only passed after an explicit per-item GO from the operator. Never ask for a blanket GO. Never propose a removal on your own.rollbackreverts files. Dry-run first (default), show the exact file list, get the GO, then--go.
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.
- 23d ago First seen · 143 lines · 131 tokens per session scan A e026fa7fd42c
refine is a skill published in the GitHub repository Ertinox7711/SGRR-AGI-V2 (1 stars, last pushed 1mo ago), licensed MIT. It adds 131 tokens to every session and 1,622 once invoked, about $0.0005 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 2026-10-04.
Other skills, from other repositories
knowledge-ingest
Ingest documents, articles, conversations, or supplied text into Knowledge with retained originals, sourced claims, entity updates, timelines, and cross-links; also learn durable lessons from a set of conversations, transcripts, or past sessions (/learn). Routes meetings to knowledge-meeting-ingest and short thoughts…
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
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…
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…