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 agentmods add skills/agentic-dev3o/devx-plugins/update-originnpx skills add agentic-dev3o/devx-plugins --skill update-origingit clone --depth 1 https://github.com/agentic-dev3o/devx-pluginsWhat 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 | $0.00052 | $0.01014 |
| Opus 5 | $0.00026 | $0.00507 |
| Sonnet 5 | $0.00010 | $0.00203 |
| Haiku 4.5 | $0.00005 | $0.00101 |
Grade A, and why
update-origin 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 yesterday.
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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Branch From Origin
Merge origin/<origin-branch> (= $ARGUMENTS, default main) into the current branch, always behind a recoverable backup.
Copy this checklist into your reply and check items off as you go:
Update Progress:
- [ ] Preflight passed (clean tree, not detached, branch ≠ target, push.default safe)
- [ ] Backup branch created
- [ ] Synced with origin/<current-branch> (if it has new commits)
- [ ] Merged origin/<target>
- [ ] Conflicts resolved
- [ ] Result verified clean
- [ ] Pushed (only if user confirmed)
- [ ] Backup deleted (success) or kept (recovery)
Guardrails (exact — do not vary)
- The working tree MUST be clean. Run
git status --porcelain; any output → stop and tell the user to commit or stash first. Do nothing else. - Stop if HEAD is detached or the current branch equals
<origin-branch>. - Back up before touching anything:
git branch backup/$(git branch --show-current)-$(git rev-parse --short HEAD). Tell the user the exact name; call it<backup>below. - Never delete
<backup>unless the final tree is verified clean and the update succeeded. - Never rebase, never force-push (
--force,--force-with-lease,+refspec— all forbidden). Several developers and agents work on the same branch; rewriting published history clobbers their work. A rejected push means new remote commits to merge in, never to overwrite. - Push only the current branch — never a bare push. A bare
git pushobeyspush.default, and undermatchingit pushes every same-named local branch. Alwaysgit push origin HEAD. Preflight hardening: rungit config push.default; ifmatchingor empty, warn the user and offergit config push.default currentfor this repo.
Phase 1 — Sync and merge
git fetch origin.- If
origin/<current-branch>exists and has commits not on HEAD (git rev-list --count HEAD..origin/<current-branch>> 0), others pushed while you worked →git merge origin/<current-branch>first. git merge origin/<origin-branch>.
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.
- yesterday First seen · 70 lines · 52 tokens per session scan A c020edd8a76c
update-origin is a skill published in the GitHub repository agentic-dev3o/devx-plugins (11 stars, last pushed 14d ago), licensed MIT. It adds 52 tokens to every session and 1,014 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…