creating-distillations

creating-distillations is a skill for Claude Code from chrisgagne/grounded-forge. It costs 98 tokens per session (2,449 once invoked), scanned A, original, MIT.

A workflow that adapts one verified reference to one defined task. It checks whether the source applies, then creates a task-specific distillation, optionally using defined lenses.

In plain words
What is it for?
It is for producing one source summary for a particular task, either during source ingestion or while building a new application.
Why use it?
It prevents every source from being copied into every task collection when it is not relevant. The applicability check keeps task-focused material limited to useful sources.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions subagents.

Part of the grounded-forge plugin — 12 skills, 2 agents, 1 hook shipped together

Good fit It is for producing one source summary for a particular task, either during source ingestion or while building a new application.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chrisgagne/grounded-forge/creating-distillations
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 chrisgagne/grounded-forge --skill creating-distillations
Clone the repo
git clone --depth 1 https://github.com/chrisgagne/grounded-forge

Made for: Claude Code.

Or install grounded-forge, the plugin that ships this one along with the rest of its 12 skills, 2 agents, 1 hook.

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 creating-distillations

README.md
[![agentmods](https://agentmods.dev/badge/skills/chrisgagne/grounded-forge/creating-distillations/github.svg)](https://agentmods.dev/skills/chrisgagne/grounded-forge/creating-distillations)
Your own site
<a href="https://agentmods.dev/skills/chrisgagne/grounded-forge/creating-distillations"><img src="https://agentmods.dev/badge/skills/chrisgagne/grounded-forge/creating-distillations/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 creating-distillations

Your own site · 80×15
<a href="https://agentmods.dev/skills/chrisgagne/grounded-forge/creating-distillations"><img src="https://agentmods.dev/badge/skills/chrisgagne/grounded-forge/creating-distillations.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,449 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 $0.00098 $0.02449
Opus 5 $0.00049 $0.01224
Sonnet 5 $0.00020 $0.00490
Haiku 4.5 $0.00010 $0.00245

Measured 9d ago against content hash 5ab85809d11a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

creating-distillations 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 9d 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.

.claude/skills/creating-distillations/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Creating Distillations

Per-distillation projection of one source onto one task axis. Consumes a (source, task) pair plus an optional lens-set; produces one file plus an index update.

Invoked by:

  • creating-applications, per-distillation orchestration: once per applicable (source, task) distillation.
  • ingesting-resources Pass G: once per task axis during a new-source ingest.

Rationale, template structure, evidence discipline, four-outcome lens-applicability gate, and failure modes live in projection-protocol.md. This file is the runbook; that one is the rationale. Read both before invoking.

When to use

  • Pass G of ingesting-resources. Per task axis in the corpus, the ingest skill calls this skill once with the new (source, task) pair. The applicability gate decides whether to produce a distillation or skip.
  • Per-distillation orchestration in creating-applications. When a new application is being assembled, the orchestrator calls this skill once per (source, task) distillation named in the task spec. Often dispatched as parallel sub-agents.
  • Operator follow-up. A new task axis has landed and the operator notices a source whose existing deep reference predates the axis: invoke this skill directly to project that source onto the new task.
  • Re-projection after a deep-ref update. The deep reference has been sharpened (often via Pass G cycling: see projection-protocol.md §Cycling); the distillation needs to reflect the updated deep.

When not to use

  • The deep reference does not yet exist. Run ingesting-resources first.
  • The task axis does not yet exist (no distillation directory, no index, no build profile). Run creating-taskscreating-applications first.
  • The operator wants to project all applicable sources onto a new axis. That's the per-distillation orchestration job inside creating-applications: invoke it instead, and it will call this skill once per source.

Read the full file on GitHub · 101 lines

Files

What ships with it

1 file 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. 9d ago First seen · 101 lines · 98 tokens per session scan A 5ab85809d11a

Subscribe to this mod's changes

creating-distillations is a skill published in the GitHub repository chrisgagne/grounded-forge (7 stars, last pushed 18d ago), licensed MIT. It adds 98 tokens to every session and 2,449 once invoked, about $0.0005 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.