sips-context-distiller

sips-context-distiller is a skill for Claude Code, Codex from RasputinKaiser/Self-Improvement-Plugin. It costs 37 tokens per session (131 once invoked), scanned A, original, MIT.

A guide for extracting short, source-linked excerpts from large files or many inputs.

In plain words
What is it for?
For scanning oversized inputs, producing bounded context packets, and following them with precise source checks when exact behavior matters.
Why use it?
It keeps the working context manageable while showing where the extracted information came from.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the harness-self-improvement plugin — 10 skills, 12 commands, 5 agents, 7 hooks, 1 MCP server shipped together

Good fit For scanning oversized inputs, producing bounded context packets, and following them with precise source checks when exact behavior matters.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rasputinkaiser/self-improvement-plugin/sips-context-distiller
Install

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.

Any agent
npx skills add RasputinKaiser/Self-Improvement-Plugin --skill sips-context-distiller
Clone the repo
git clone --depth 1 https://github.com/RasputinKaiser/Self-Improvement-Plugin

Made for: Claude Code, Codex.

Or install harness-self-improvement, the plugin that ships this one along with the rest of its 10 skills, 12 commands, 5 agents, 7 hooks, 1 MCP server.

Wrote 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.

agentmods badge for sips-context-distiller

README.md
[![agentmods](https://agentmods.dev/badge/skills/rasputinkaiser/self-improvement-plugin/sips-context-distiller.svg)](https://agentmods.dev/skills/rasputinkaiser/self-improvement-plugin/sips-context-distiller)
Your own site
<a href="https://agentmods.dev/skills/rasputinkaiser/self-improvement-plugin/sips-context-distiller"><img src="https://agentmods.dev/badge/skills/rasputinkaiser/self-improvement-plugin/sips-context-distiller.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 131 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00037 $0.00131
Opus 5 $0.00018 $0.00066
Sonnet 5 $0.00007 $0.00026
Haiku 4.5 $0.00004 $0.00013

Measured 8d ago against content hash aaa7d143b6e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

sips-context-distiller 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 8d 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.

skills/sips-context-distiller/SKILL.md · 13 lines

What it actually says

SIPS Context Distiller

Use homebase_context_scan to find context-drain risks and homebase_distill_context to extract bounded excerpts from the relevant files.

Keep excerpts source-linked with paths and line references where possible. Mark omissions explicitly; a distilled packet is working context, not full-file proof.

If exact behavior matters, follow the distilled packet by reading the precise source lines before editing or making a final claim.

Files

What ships with it

3 files 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.

Changes

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.

  1. 8d ago First seen · 13 lines · 37 tokens per session scan A aaa7d143b6e6

Subscribe to this mod's changes

sips-context-distiller is a skill published in the GitHub repository RasputinKaiser/Self-Improvement-Plugin (8 stars, last pushed 10d ago), licensed MIT. It adds 37 tokens to every session and 131 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.

Related

Other skills, from other repositories

taiyi-compress

A workflow tool for shrinking large coding-agent conversations and work files into shorter context notes. It can also coordinate separate agents for parallel development and create handoff notes for continuing work in a new session.

Dong90/oh-my-taiyiforge · 51 tokens

continuous-learning-v2

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.

sangrokjung/claude-forge · 33 tokens

agentic-os

A design for running persistent specialist agents, commands, scripts, and file-based memory inside Codex. It keeps the setup in project files so it can continue across sessions.

mturac/everything-openai-codex · 94 tokens

codebase-memory-mcp

Resolve canonical Git checkouts, index and verify codebase-memory-mcp graphs through the guarded CLI, and safely audit duplicate worktree caches. Use when a user mentions codebase memory MCP, searchgraph, tracepath, indexrepository, worktree indexes, or oversized graph caches.

vincentkoc/dotskills · 62 tokens

project-memory

Initialize, retrieve, and explicitly update the separate Rootloom Memory plugin's repository-owned architecture, risk, decision, and failure lessons. Use only when explicitly requested. Memory is experimental, advisory, and outside Rootloom Core.

qingye-lab/rootloom · 47 tokens

memory-hygiene

Keep agent-written memory files from rotting. Audits /.claude/projects/ /memory/ for facts the tree now contradicts — stale version pins, passed sequence facts, vanished paths — plus MEMORY.md index drift, and enforces the memory format contract at write time. Use when the user says "audit my memory", "memory is…

alexmond/alexmskills · 103 tokens