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 chrisgagne/grounded-forge --skill creating-distillationsgit clone --depth 1 https://github.com/chrisgagne/grounded-forgeWrote 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/chrisgagne/grounded-forge/creating-distillations)<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.
<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>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 | $0.00098 | $0.02449 |
| Opus 5 | $0.00049 | $0.01224 |
| Sonnet 5 | $0.00020 | $0.00490 |
| Haiku 4.5 | $0.00010 | $0.00245 |
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.
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-resourcesPass 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-resourcesfirst. - The task axis does not yet exist (no distillation directory, no index, no build profile). Run
creating-tasks→creating-applicationsfirst. - 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.
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.
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.
- 9d ago First seen · 101 lines · 98 tokens per session scan A 5ab85809d11a
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.
Other skills, from other repositories
warpp-workflow-authoring
Author WARPP workflows for Manifold as typed-port dataflow JSON. Use when a user asks to build, create, design, generate, or edit a Flow / workflow / automation / pipeline / DAG in Manifold, or mentions WARPP, workflow nodes, or the /flow builder. Covers the document format, port types and coercions, the builtin node…
manifold-api
Use when an agent needs to inspect or call the local Manifold HTTP API. Provides guidelines and scripts to filter specs before reading and handle payloads safely.
duckduckgo-search
Free keyless web, news, and image search via ddgs.
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
mcporter
List, auth, and call MCP servers/tools from the terminal.
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.…