upstream-contribute

upstream-contribute is a skill for Claude Code from Rockielab/rockie-claude. It costs 106 tokens per session (3,091 once invoked), scanned A, original, Apache-2.0.

A contribution workflow for the Rockie coding-agent system. It finds reusable improvements from a work session, packages them for local review or prepares a public pull request, and waits for human approval before pushing.

In plain words
What is it for?
Preparing a patch for a local Rockie copy, generalising a useful pattern for other users, and opening a contribution to the Rockielab/rockie-claude project.
Why use it?
It turns useful fixes and patterns discovered during local work into reviewable changes without automatically merging or publishing them.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the rockie-claude plugin — 29 skills, 1 MCP server shipped together

Good fit Preparing a patch for a local Rockie copy, generalising a useful pattern for other users, and opening a contribution to the Rockielab/rockie-claude project.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rockielab/rockie-claude/upstream-contribute
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 Rockielab/rockie-claude --skill upstream-contribute
Clone the repo
git clone --depth 1 https://github.com/Rockielab/rockie-claude

Made for: Claude Code.

Or install rockie-claude, the plugin that ships this one along with the rest of its 29 skills, 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 upstream-contribute

README.md
[![agentmods](https://agentmods.dev/badge/skills/rockielab/rockie-claude/upstream-contribute/github.svg)](https://agentmods.dev/skills/rockielab/rockie-claude/upstream-contribute)
Your own site
<a href="https://agentmods.dev/skills/rockielab/rockie-claude/upstream-contribute"><img src="https://agentmods.dev/badge/skills/rockielab/rockie-claude/upstream-contribute/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 upstream-contribute

Your own site · 80×15
<a href="https://agentmods.dev/skills/rockielab/rockie-claude/upstream-contribute"><img src="https://agentmods.dev/badge/skills/rockielab/rockie-claude/upstream-contribute.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,091 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 $0.00106 $0.03091
Opus 5 $0.00053 $0.01545
Sonnet 5 $0.00021 $0.00618
Haiku 4.5 $0.00011 $0.00309

Measured 12d ago against content hash 7a563036fc6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

upstream-contribute 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 12d 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.

project-harness/skills/upstream-contribute/SKILL.md · 310 lines

How it starts

The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/upstream-contribute — meta-loop: rockie users improve rockie

/upstream-contribute covers two contribution modes:

  • Local harness patch — package an improvement against the user's own local rockie clone as a reviewed patch proposal.
  • Public upstream PR — generalize the pattern and dispatch a PR against Rockielab/rockie-claude so the next release ships it to everyone.

This is the meta-loop. Researchers using rockie-claude in their own work uncover patterns that generalize — a tighter [DEAD-END] query, a hook that catches a stuck-detector edge case, a skill that helps across disciplines. The skill captures one of those, generalizes it, and opens a reviewable PR. The maintainers merge; the next user benefits.

When to run

  • The user says "upstream this", "contribute back", "anything generalizable here", "open-source this", "propose a harness change", or "write a PR for rockie".
  • /clean finishes an audit and emits the post-audit nudge (see clean/SKILL.md → "Post-audit hook").
  • A [LEARN harness-upstream] or [LEARN cross-discipline] block was written this session and the user wants to act on it.

Run at most once per session, near the end. Don't dispatch the writer sub-agent during active work — the user wants to review the candidates before any forking happens.

Method

The skill uses Scout / Generator / Verifier / Updater separation. The proposing agent never verifies and commits its own change.

1. Scout (this skill, in-session)

Read recent context to identify candidates:

# [LEARN] rows added this session
sqlite3 ${OPENCLAW_WORKSPACE_DIR}/memory/workflow.db "
  SELECT category, rule, mistake, correction
  FROM learnings
  WHERE created_at >= datetime('now','-6 hours')
  ORDER BY created_at DESC
"

# Files changed in the last N commits
git log --since='6 hours ago' --name-only --pretty=format:'%h %s'

# Any new skill / hook / script files
git diff --name-only HEAD~5..HEAD -- '${OPENCLAW_SKILLS_DIR}/' '${OPENCLAW_WORKSPACE_DIR}/hooks/' '${OPENCLAW_WORKSPACE_DIR}/scripts/' \
  | grep -E '\.(md|sh|py)$' || true

Read the full file on GitHub · 310 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. 12d ago First seen · 310 lines · 106 tokens per session scan A 7a563036fc6c

Subscribe to this mod's changes

upstream-contribute is a skill published in the GitHub repository Rockielab/rockie-claude (21 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 106 tokens to every session and 3,091 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 2026-08-30.

Related

Other skills, from other repositories

git-commit

A guided Git commit workflow that examines changes and creates a commit message using the Conventional Commits format, a shared style for labeling changes such as features, fixes, tests, or documentation.

adongwanai/learn-workbuddy · 0 tokens

pi-sync

Daily upstream-sync job for the pi Go port — fetch upstream pi, triage every change since the recorded pin, port what's in scope, verify idiomatic + parity via independent reviews, update the ledger, and push. Use for "sync with upstream", "porting job", or as the scheduled daily run.

sky-valley/pi · 66 tokens

release-doi

A release procedure for research repositories that publish versions with a DOI, a permanent identifier for scholarly work, through Zenodo.

shimo4228/claude-harness · 126 tokens

harness-sync

A one-way synchronisation process for exporting selected parts of a local AI harness to public Git repositories. It removes runtime files, checks metadata, scans for secrets, and copies approved components.

shimo4228/claude-harness · 194 tokens

git-workflow

A set of operating rules for running Git commands in Bash in this environment. It explains command forms that avoid unnecessary permission prompts and notes the extra restrictions around pushing changes.

shimo4228/claude-harness · 108 tokens

auto-run

Autonomous personalized research loop. Use when the user wants to research a topic autonomously, run a research loop, start adaptive research, or use presets like technique-scout or cross-domain. Triggers on: 'auto run', 'research loop', 'autonomous research', 'run research', 'start research', 'adaptive research'.

primeline-ai/claude-adaptive-research · 70 tokens