OPOS: Skill for Claude Code

.claude/skills/propose-to-core/SKILL.md

propose-to-core is a skill for Claude Code from Koroqe/OPOS. It costs 51 tokens per session (3,262 once invoked), scanned A, original, MIT.

A workflow that turns a defect found in a framework file into an anonymized pull request for the upstream OPOS repository.

In plain words
What is it for?
Use it manually for a history entry or let `review-history` invoke it for upstream-worthy defects. Dry-run mode shows the proposed pull request without changing remote repositories.
Why use it?
It provides classification, drafting, and two redaction checks before any branch, fork, push, or pull-request creation happens outside the local machine.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is Koroqe/OPOS's own configuration. It tells Claude Code how to work on OPOS itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything OPOS configures →

View source ↗ Koroqe/OPOS
Reuse

Borrowing it

Nothing to install: this file belongs to Koroqe/OPOS. 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/Koroqe/OPOS/main/.claude/skills/propose-to-core/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Koroqe/OPOS

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.

agentmods badge for propose-to-core

README.md
[![agentmods](https://agentmods.dev/badge/skills/koroqe/opos/propose-to-core/github.svg)](https://agentmods.dev/skills/koroqe/opos/propose-to-core)
Your own site
<a href="https://agentmods.dev/skills/koroqe/opos/propose-to-core"><img src="https://agentmods.dev/badge/skills/koroqe/opos/propose-to-core/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 propose-to-core

Your own site · 80×15
<a href="https://agentmods.dev/skills/koroqe/opos/propose-to-core"><img src="https://agentmods.dev/badge/skills/koroqe/opos/propose-to-core.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,262 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 $0.00051 $0.03262
Opus 5 $0.00026 $0.01631
Sonnet 5 $0.00010 $0.00652
Haiku 4.5 $0.00005 $0.00326

Measured 9d ago against content hash d365580fc845, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

propose-to-core 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/propose-to-core/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

propose-to-core

When to use

  • Invoked by review-history's triage when an open delta targets an upstreamable (CORE) file — the scheduled path.
  • Manually: /propose-to-core <history-entry-path> or /propose-to-core --delta-target <path> --problem "<generic defect description>".
  • --dry_run runs everything up to and including the adversarial redaction review, prints the would-be PR (title, body, diff, both gate verdicts), and touches nothing remote.

The outbound-write invariant (named, load-bearing)

No git push, gh repo fork, gh pr create, or any other write that leaves this machine occurs before BOTH redaction gates have passed: the deterministic pre-gate (step 4b) AND the literal REDACTION: PASS line from the redaction-reviewer agent (step 5). Any future edit to this skill that reorders an outbound write ahead of the gates is a defect by definition.

Run records (sub-invocation rule)

Manual invocations write a run record to ./history/ (root-CLAUDE.md schema). When invoked as a sub-step of a scheduled review-history run (the prelude string belongs to the parent), this skill writes no separate run record — the parent's scheduled-run entry plus this skill's proposals/LEDGER.md line ARE the record. The prelude routing convention applies to direct invocations only.

Inputs — validated before ANY use (they feed shell commands, gh api paths, branch names, and PR titles)

  • entry_path (optional): must resolve to a file inside the repo root — reject .., absolute paths outside the root, symlinks escaping the root.
  • delta_target (optional; inferable from the entry's delta_target: field or its proposed_delta text): repo-relative, no leading /, no .., charset [A-Za-z0-9._/-] only.
  • dry_run (optional bool; default false).
  • Slugs are ALWAYS re-derived by sanitizing the upstream file path to [a-z0-9-] — never taken from delta free text.

Steps

1. Resolve the delta

Read the entry (or the inline --problem). Extract the defect description and the delta_target. No inferable target → stop with guidance to supply --delta-target.

Read the full file on GitHub · 121 lines

Files

What ships with it

6 files 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 · 121 lines · 51 tokens per session scan A d365580fc845

Subscribe to this mod's changes

propose-to-core is a skill published in the GitHub repository Koroqe/OPOS (2 stars, last pushed 7d ago), licensed MIT. It adds 51 tokens to every session and 3,262 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

github

GitHub via gh CLI: PRs, issues, reviews, repos, auth.

NousResearch/hermes-agent · 19 tokens

github

Full GitHub CLI control — issues, PRs, code reviews, repo management. Uses gh CLI with auth detection, rate limiting, and templates. Triggers on: github, issue, pull request, PR, code review, repo, branch, label, assignee, milestone, release, workflow, actions.

adolfousier/opencrabs · 0 tokens

release

Release gentle-pi through GitHub and npm. Trigger: release, publish, npm publish, GitHub release, version bump.

Gentleman-Programming/gentle-pi · 28 tokens

pre-publish-review

Nuclear-grade 12-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm release, spawns up to 10 ultrabrain agents for deep per-change analysis, invokes /review-work (orchestrator manual QA plus one gate reviewer) for holistic review, and 1 oracle for overall release…

code-yeongyu/oh-my-openagent · 161 tokens

parallel-pr-review

Use when asked to "review the open PRs", review a batch or stack of pull requests, or run a recurring PR-review pass on a repo — especially with many PRs, stacked branches, conflicts, or security-sensitive changes. Covers grouping, fan-out to review subagents, verdict synthesis, and posting.

suyoumo/ClawProBench · 67 tokens

Release Notes Generator

Generate professional software release notes from a commit log: classify changes, write user-facing summaries, draft a publishable announcement, and assess release readiness. Use for release, changelog, version, and deploy requests.

AgentEra/Agently · 46 tokens