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 Rockielab/rockie-codex --skill upstream-contributegit clone --depth 1 https://github.com/Rockielab/rockie-codexWrote 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/rockielab/rockie-codex/upstream-contribute)<a href="https://agentmods.dev/skills/rockielab/rockie-codex/upstream-contribute"><img src="https://agentmods.dev/badge/skills/rockielab/rockie-codex/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.
<a href="https://agentmods.dev/skills/rockielab/rockie-codex/upstream-contribute"><img src="https://agentmods.dev/badge/skills/rockielab/rockie-codex/upstream-contribute.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 | $0.00169 | $0.03135 |
| Opus 5 | $0.00084 | $0.01568 |
| Sonnet 5 | $0.00034 | $0.00627 |
| Haiku 4.5 | $0.00017 | $0.00314 |
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 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 — 295 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
$propose-harness-change packages improvements against the user's
own local clone of rockie-codex. $upstream-contribute is the
public counterpart: it dispatches a PR against saml212/rockie-codex
so the next release ships the pattern to everyone.
This is the meta-loop. Researchers using rockie-codex 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".
$cleanfinishes an audit and emits the post-audit nudge (seeclean/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.
Codex doesn't expose repo-defined slash commands the way Claude
Code does, so the practical invocation path is $upstream-contribute
or natural language ("contribute back upstream").
Method
The skill mirrors the Generator / Verifier / Updater rigor of
$propose-harness-change and adds a Scout step in front (since
the upstream PR is a more public artifact than a local patch).
1. Scout (this skill, in-session)
Read recent context to identify candidates:
# [LEARN] rows added this session
/usr/bin/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
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 · 295 lines · 169 tokens per session scan A ed91f89b1435
upstream-contribute is a skill published in the GitHub repository Rockielab/rockie-codex (20 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 169 tokens to every session and 3,135 once invoked, about $0.0008 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…