What is importing-upstream-content?

A workflow for bringing skills, agents, and reference files from an upstream project into a bundled collection. Upstream means the original outside project that publishes the material.

Use it when importing or updating content from projects such as compound-engineering, agent-browser, or other third-party sources, while recording its source and applying local quality gates.

Imported content needs licensing, provenance, adaptation, and compatibility checks, especially when it is shipped to every user. The workflow also distinguishes a new import, a refresh, and a targeted improvement.

How marcusrbrown/systematic configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to marcusrbrown/systematic. 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/marcusrbrown/systematic/main/.agents/skills/importing-upstream-content/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/marcusrbrown/systematic

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/marcusrbrown/systematic/importing-upstream-content/github.svg)](https://agentmods.dev/skills/marcusrbrown/systematic/importing-upstream-content)

Your own site

<a href="https://agentmods.dev/skills/marcusrbrown/systematic/importing-upstream-content"><img src="https://agentmods.dev/badge/skills/marcusrbrown/systematic/importing-upstream-content/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/marcusrbrown/systematic/importing-upstream-content"><img src="https://agentmods.dev/badge/skills/marcusrbrown/systematic/importing-upstream-content.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,010 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.

Model	Per session	Once invoked
Fable 5.1	$0.00077	$0.02010
Opus 5.5	$0.00031	$0.00804
Sonnet 5.5	$0.00015	$0.00402
Haiku 4.5	$0.00008	$0.00201

Measured today against content hash ed2a7bb4f972, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

importing-upstream-content 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 today.

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/importing-upstream-content/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Importing Upstream Content

Overview

Imported content ships to every Systematic user. It must pass the same gates as content written here. It must also carry its licence and record the upstream commit it came from. The detailed rules live in the solution docs listed at the end. This skill collects them into one checklist, with emphasis on the steps importers usually miss.

Choose the mode

Situation	Mode	Rule
A skill or agent new to Systematic	Import with light adaptation	Keep the upstream voice. Adapt only what the gates and harnesses require.
A newer upstream release of content already imported	Refresh	Diff the old pinned commit against the new one, and apply that diff onto Systematic's copy. Re-apply Systematic's additions. Never copy the upstream files over the top.
One upstream improvement to a skill Systematic has changed	Merge	Port the capability and keep Systematic's structure. Keep one authority per section.
A file that ships inside an npm package and needs only a mechanical transform	Generated surface	Pin the package exactly as a devDependency, write a generator, and register it in `scripts/lib/generated-surfaces.ts`. The pin is the npm version, not a commit SHA. Renovate brings refreshes, and `surfaces:regen` applies them. The generator writes the version into `ATTRIBUTIONS.md`. Don't edit any of these by hand; the SHA and human-review steps below don't apply.

Get the upstream source

Pin a full 40-character commit SHA. Resolve a tag or short SHA first. Every later step cites the full SHA.
Recreate the clone if it's missing. .slim/clonedeps.json lists each clone's repo URL, ref and path. .slim/clonedeps/repos/ is gitignored and often absent. Clone the repo at that ref into that path, or fetch the files at the pinned SHA with gh api. Never import from memory or from a summary.
For a refresh, check the base first. Confirm that the old pinned SHA in ATTRIBUTIONS.md is the commit you are diffing from. If it isn't, stop.
Search history with git log --all --grep or tags. At HEAD, a path-limited git log shows only the branch-root commit for content older than 2026-07-31.

Read the full file on GitHub · 112 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.

today First seen · 112 lines · 77 tokens per session scan A ed2a7bb4f972

Subscribe to this mod's changes

importing-upstream-content is a skill published in the GitHub repository marcusrbrown/systematic (28 stars, last pushed today), licensed MIT. It adds 77 tokens to every session and 2,010 once invoked, about $0.0003 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 2026-11-06.

Building agents ai bun opencode plugin semantic-release systematic

importing-upstream-content next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
importing-upstream-contentmarcusrbrown/systematic	Skill	28	today	MIT	A	77	Claude Code
plan-protocolkdcokenny/ocx	Skill	980	1mo ago	MIT	A	14	Claude Code, Codex
plan-reviewkdcokenny/ocx	Skill	980	1mo ago	MIT	A	11	Claude Code, Codex
opencode-ensemblehueyexe/opencode-ensemble	Skill	254	18d ago	MIT	A	42	Claude Code, Codex
code-reviewkdcokenny/ocx	Skill	980	1mo ago	MIT	A	14	Claude Code, Codex
code-philosophykdcokenny/ocx	Skill	980	1mo ago	MIT	A	32	Claude Code, Codex
frontend-philosophykdcokenny/ocx	Skill	980	1mo ago	MIT	A	36	Claude Code, Codex

systematic: Skill for Claude Code