repo-native-alignment: Skill for Claude Code

.agents/skills/distill/SKILL.md

distill is a skill for Claude Code, Codex from open-horizon-labs/repo-native-alignment. It costs 47 tokens per session (1,803 once invoked), scanned A, original, MIT.

A human-led review method for cleaning up knowledge and safeguards collected across coding sessions.

In plain words
What is it for?
Use it after several sessions, before a new project phase, or when repeated lessons from earlier work need to be organized.
Why use it?
It reduces noisy or repeated search results by deciding which lessons to keep, combine, promote, or discard.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is open-horizon-labs/repo-native-alignment's own configuration. It tells Claude Code and Codex how to work on repo-native-alignment itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything repo-native-alignment configures →

Reuse

Borrowing it

Nothing to install: this file belongs to open-horizon-labs/repo-native-alignment. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/open-horizon-labs/repo-native-alignment/main/.agents/skills/distill/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/open-horizon-labs/repo-native-alignment

Made for: Claude Code, Codex.

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 distill

README.md
[![agentmods](https://agentmods.dev/badge/skills/open-horizon-labs/repo-native-alignment/distill/github.svg)](https://agentmods.dev/skills/open-horizon-labs/repo-native-alignment/distill)
Your own site
<a href="https://agentmods.dev/skills/open-horizon-labs/repo-native-alignment/distill"><img src="https://agentmods.dev/badge/skills/open-horizon-labs/repo-native-alignment/distill/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.

agentmods 80×15 button for distill

Your own site · 80×15
<a href="https://agentmods.dev/skills/open-horizon-labs/repo-native-alignment/distill"><img src="https://agentmods.dev/badge/skills/open-horizon-labs/repo-native-alignment/distill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,803 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 $0.00047 $0.01803
Opus 5 $0.00023 $0.00901
Sonnet 5 $0.00009 $0.00361
Haiku 4.5 $0.00005 $0.00180

Measured 11d ago against content hash 0cb991d68dc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

distill 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 11d 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.

.agents/skills/distill/SKILL.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/distill

Surface patterns in accumulated knowledge. Propose what to keep, promote, compact, or dismiss. The human decides.

Distill is the complement to /salvage: salvage extracts learning from a single session; distill curates the corpus those extractions build over time. Without distill, metis accumulates but never compounds.

When to Use

Invoke /distill when:

  • After multiple sessions - The corpus has grown and hasn't been reviewed
  • Before a new phase - Want to know what's actually settled before moving forward
  • Search results feel noisy - RNA search returns too much loosely-related content
  • Similar learnings keep appearing - /salvage keeps extracting the same insights (the meta-signal)
  • End of a successful session - Even good sessions produce learnings worth capturing before context is lost

Use distill (not /salvage) when the session went well. /salvage is for stopping because things went wrong. Distill is for pausing because things went right — or simply finished — and learnings are worth capturing before context is lost.

Do not use when: You're in the middle of execution. Distill is a pause point, not a mid-flight activity.

The Human-Led Curation Principle

Distill leverages LLMs for what they're good at — pattern recognition, clustering, surfacing similar entries — while keeping judgment with the human.

LLMs do: find recurring themes, group similar entries, surface candidates. Humans do: decide what matters, what's worth promoting, what's stale or context-specific.

Auto-promotion is never correct. A theme proposal is not a guardrail until a human writes it.

The Process

Step 1: Establish Scope

Decide what corpus to work with:

  • Session scope (default, no RNA needed): learnings from this conversation
  • Corpus scope (RNA available): accumulated metis across all sessions, optionally filtered by outcome, phase, or tag

Step 2: Surface Candidates

Session scope: Review the conversation. What was learned? What assumptions were validated or invalidated? What constraints were discovered? What would be useful to know at the start of the next session?

Read the full file on GitHub · 170 lines

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. 11d ago First seen · 170 lines · 47 tokens per session scan A 0cb991d68dc5

Subscribe to this mod's changes

distill is a skill published in the GitHub repository open-horizon-labs/repo-native-alignment (5 stars, last pushed 2d ago), licensed MIT. It adds 47 tokens to every session and 1,803 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

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

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.…

mem0ai/mem0 · 273 tokens

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…

danielmiessler/LifeOS · 196 tokens

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.

opensquilla/opensquilla · 44 tokens

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…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens