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 PaulRBerg/agent-skills --skill rebasegit clone --depth 1 https://github.com/PaulRBerg/agent-skillsWrote 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/paulrberg/agent-skills/rebase)<a href="https://agentmods.dev/skills/paulrberg/agent-skills/rebase"><img src="https://agentmods.dev/badge/skills/paulrberg/agent-skills/rebase/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/paulrberg/agent-skills/rebase"><img src="https://agentmods.dev/badge/skills/paulrberg/agent-skills/rebase.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 | $0.00049 | $0.02838 |
| Opus 5.5 | $0.00020 | $0.01135 |
| Sonnet 5.5 | $0.00010 | $0.00568 |
| Haiku 4.5 | $0.00005 | $0.00284 |
Grade A, and why
rebase-skill 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 24d 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rebase Skill
Update one skills/<name>/ from its external source while keeping local customizations layered over the upstream
content. Here, "rebase" means a three-way content merge. It does not mean rewriting this repository's Git history.
Invocation and Authority
Run only when the user explicitly invokes @rebase-skill, asks to rebase a named skill from its external source, or
when the scheduled caller in Scheduled Runs invokes it. General maintenance requests, discovered
upstream releases, and another skill's recommendations do not authorize this workflow. Do not schedule it elsewhere or
invoke it autonomously.
User instructions take precedence over this skill. An apply request authorizes the selected update through validation,
commit, and publication under repository rules. A preview request or --dry-run permits inspection and a proposed diff
only. It does not authorize repository edits, provenance updates, commits, or publication.
@rebase-skill <skill-name> [--source <repository-url>] [--path <upstream-skill-path>] [--ref <ref>] [--dry-run]
Examples:
@rebase-skill grill-me --dry-run
@rebase-skill retro --source <repository-url> --path <upstream-skill-path> --ref <tag-or-commit>
Require one existing local skill. Resolve omitted source details from provenance and import history. Never infer a
source from a matching skill name alone. Without --ref, use the source repository's current default-branch tip.
Resolve the target ref to a full commit ID before comparison.
Scheduled Runs
The user authorized one scheduled caller. Circadian's weekly skill-upstream-rebase task runs this workflow in apply
mode for every skill discovered by jobs/rebase-upstream-skills.sh. Each run discovers the union of README "Forked
Skills" rows and active .agents/skill-upstreams/<name>.md records from fresh origin/main. It excludes the provenance
index and deduplicates names. No per-skill scheduler list needs an update.
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.
- 24d ago First seen · 200 lines · 49 tokens per session scan A bd2c1fddccf4
rebase-skill is a skill published in the GitHub repository PaulRBerg/agent-skills (104 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 2,838 once invoked, about $0.0002 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 2026-10-16.
rebase-skill compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| rebase-skillPaulRBerg/agent-skills | Skill | 104 | 2d ago | MIT | A | 49 | Claude Code, Codex |
| merge-batchdiegosouzapw/OmniRoute | Skill | 85k | yesterday | MIT | A | 46 | Claude Code |
| prowler-commitprowler-cloud/prowler | Skill | 15k | today | Apache-2.0 | A | 44 | Claude Code, Codex |
| gh-auth-isolationgithub/gh-aw | Skill | 5.6k | today | MIT | A | 20 | Claude Code, Codex |
| comet-githubrpamis/comet | Skill | 3.3k | today | MIT | A | 72 | Claude Code, Codex |
| github-skillzeenie-ai/OpenCompany | Skill | 1.1k | 4d ago | MIT | A | 51 | Claude Code |
| re0-mergeLilMGenius/paperthin | Skill | 1.4k | today | MIT | A | 70 | Claude Code |