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.
git 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/commands/ertinox7711/sgrr-agi-v2/refine)<a href="https://agentmods.dev/commands/ertinox7711/sgrr-agi-v2/refine"><img src="https://agentmods.dev/badge/commands/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/commands/ertinox7711/sgrr-agi-v2/refine"><img src="https://agentmods.dev/badge/commands/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 | $0.00038 | $0.00354 |
| Opus 5.5 | $0.00015 | $0.00142 |
| Sonnet 5.5 | $0.00008 | $0.00071 |
| Haiku 4.5 | $0.00004 | $0.00035 |
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 21d 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
Run the continual harness refinement on this session. Invoke the refine
skill and follow it exactly.
Arguments: $ARGUMENTS
Routing:
--status/--list/--rollback <id>-> read-only inspection path of the skill (harness-refine.py status|list|show|rollback). A rollback is dry-run first; it only runs with--goafter the operator gives a per-file GO.- otherwise -> the full refine procedure: check state, find trajectory evidence, snapshot, write the real files, record the payload, report.
Default scope is global for cross-session lessons. Pass --local for
session/project state. If the lesson is project-specific, the entry title or
content must name the project, or it goes local.
Non-negotiable on this rig: the base ~/.claude/CLAUDE.md is immutable, and
delete edits are refused by the engine unless the operator gave an explicit
per-item GO. Additive only by default.
Max 3 edits unless asked for more. No evidence in this trajectory = no edit, and say so in one line rather than inventing one.
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.
- 21d ago First seen · 30 lines · 38 tokens per session scan A 4c1667e6137f
refine is a command published in the GitHub repository Ertinox7711/SGRR-AGI-V2 (1 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 354 once invoked, about $0.0002 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 commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
memory-store
Store an insight, decision, or pattern to memory.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.
lians-recall
Recall current (non-stale) facts from Lians memory, optionally as-of a past date.