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 AndrewDongminYoo/rn-agents-kit --skill rn-upgrade-pulsegit clone --depth 1 https://github.com/AndrewDongminYoo/rn-agents-kitWrote 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/andrewdongminyoo/rn-agents-kit/rn-upgrade-pulse)<a href="https://agentmods.dev/skills/andrewdongminyoo/rn-agents-kit/rn-upgrade-pulse"><img src="https://agentmods.dev/badge/skills/andrewdongminyoo/rn-agents-kit/rn-upgrade-pulse/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/andrewdongminyoo/rn-agents-kit/rn-upgrade-pulse"><img src="https://agentmods.dev/badge/skills/andrewdongminyoo/rn-agents-kit/rn-upgrade-pulse.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 | $0.00098 | $0.07115 |
| Opus 5.5 | $0.00039 | $0.02846 |
| Sonnet 5.5 | $0.00020 | $0.01423 |
| Haiku 4.5 | $0.00010 | $0.00711 |
Grade A, and why
rn-upgrade-pulse 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 2mo 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RN Upgrade Pulse
Overview
This skill records a fixed set of upgrade inputs before an agent changes a React Native or Expo project: the manifests, lockfiles, app-level and native configuration, Node pins and CI files that references/commands.md names, and nothing else.
It reports installed version evidence, package-manager and lockfile candidates, native ownership, configuration seams, and the verification commands the project already declares.
It does not select a target version, arbitrate between competing sources, or apply an upgrade.
When to Use
- "what will this React Native upgrade touch?"
- "assess this Expo SDK upgrade before we start"
- "prepare an upgrade plan for this app or workspace"
- "find the risky native and dependency areas before a version bump"
Prerequisites
- An identified repository and app root.
- The app root inside a git worktree: native ownership evidence comes from
git check-ignoreandgit ls-files, which fail outside one. rg(ripgrep) for the discovery commands that search by pattern, and Node.js 18.3.0 or later for the bundled helper, which usesnode:utilparseArgs.- Access to the project manifests, lockfiles, native directories, and existing CI scripts.
- A redacted copy of every file whose contents a row prints. No such row reads an original: the user decides once per file what a copy contains, and a file with no copy is reported as an unread input rather than read anyway.
- The bundled helpers are the exception, because each reads a file itself and prints a bounded result rather than the file. The rows that take an original need no copy, and
references/commands.mdis where they are named; do not ask for one and do not skip those files for want of one.
Quick Steps
Each step names rows from references/commands.md by intent.
That file holds every command body, so a glob set has one home.
1 — Set the selected paths
REPO_DIR=/absolute/path/to/repository
APP_DIR="$REPO_DIR/path/to/app"
SKILL_DIR=/absolute/path/to/this/skill
What ships with it
60 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.
- adapters.mjs 57 KB runs code
- evidence.mjs 23 KB runs code
- evidence.test.mjs 94 KB runs code
- references/commands.md 35 KB
- rn-upgrade-pulse.mjs 18 KB runs code
- rn-upgrade-pulse.test.mjs 38 KB runs code
- vendor/js-yaml/dist/js-yaml.mjs 106 KB runs code
- vendor/js-yaml/LICENSE 1.1 KB
- vendor/js-yaml/package.json 1.7 KB
- vendor/README.md 5.3 KB
- vendor/smol-toml/dist/date.js 4.8 KB runs code
- vendor/smol-toml/dist/error.js 2.7 KB runs code
- vendor/smol-toml/dist/extract.js 3.3 KB runs code
- vendor/smol-toml/dist/index.js 1.8 KB runs code
- vendor/smol-toml/dist/parse.js 5.6 KB runs code
- vendor/smol-toml/dist/primitive.js 11 KB runs code
- vendor/smol-toml/dist/stringify.js 7.1 KB runs code
- vendor/smol-toml/dist/struct.js 6.8 KB runs code
- vendor/smol-toml/dist/util.js 3.3 KB runs code
- vendor/smol-toml/LICENSE 1.5 KB
- vendor/smol-toml/package.json 1.5 KB
- vendor/yaml/dist/compose/compose-collection.js 3.5 KB runs code
- vendor/yaml/dist/compose/compose-doc.js 1.6 KB runs code
- vendor/yaml/dist/compose/compose-node.js 4.2 KB runs code
- vendor/yaml/dist/compose/compose-scalar.js 3.4 KB runs code
- vendor/yaml/dist/compose/composer.js 8.5 KB runs code
- vendor/yaml/dist/compose/resolve-block-map.js 5.0 KB runs code
- vendor/yaml/dist/compose/resolve-block-scalar.js 7.3 KB runs code
- vendor/yaml/dist/compose/resolve-block-seq.js 1.8 KB runs code
- vendor/yaml/dist/compose/resolve-end.js 1.2 KB runs code
- vendor/yaml/dist/compose/resolve-flow-collection.js 8.7 KB runs code
- vendor/yaml/dist/compose/resolve-flow-scalar.js 7.2 KB runs code
- vendor/yaml/dist/compose/resolve-props.js 5.4 KB runs code
- vendor/yaml/dist/compose/util-contains-newline.js 1.1 KB runs code
- vendor/yaml/dist/compose/util-empty-scalar-position.js 850 B runs code
- vendor/yaml/dist/compose/util-flow-indent-check.js 547 B runs code
- vendor/yaml/dist/compose/util-map-includes.js 471 B runs code
- vendor/yaml/dist/doc/anchors.js 2.3 KB runs code
- vendor/yaml/dist/doc/applyReviver.js 1.9 KB runs code
- vendor/yaml/dist/doc/createNode.js 3.1 KB runs code
- vendor/yaml/dist/doc/directives.js 6.1 KB runs code
- vendor/yaml/dist/doc/Document.js 13 KB runs code
- vendor/yaml/dist/errors.js 2.1 KB runs code
- vendor/yaml/dist/index.js 1.7 KB runs code
- vendor/yaml/dist/log.js 459 B runs code
- vendor/yaml/dist/nodes/addPairToJSMap.js 2.3 KB runs code
- vendor/yaml/dist/nodes/Alias.js 3.8 KB runs code
- vendor/yaml/dist/nodes/Collection.js 5.1 KB runs code
- vendor/yaml/dist/nodes/identity.js 1.8 KB runs code
- vendor/yaml/dist/nodes/Node.js 1.3 KB runs code
- vendor/yaml/dist/nodes/Pair.js 1.2 KB runs code
- vendor/yaml/dist/nodes/Scalar.js 759 B runs code
- vendor/yaml/dist/nodes/toJS.js 1.3 KB runs code
- vendor/yaml/dist/nodes/YAMLMap.js 5.0 KB runs code
- vendor/yaml/dist/nodes/YAMLSeq.js 3.6 KB runs code
- vendor/yaml/dist/parse/cst-scalar.js 9.2 KB runs code
- vendor/yaml/dist/parse/cst-stringify.js 1.8 KB runs code
- vendor/yaml/dist/parse/cst-visit.js 3.9 KB runs code
- vendor/yaml/dist/parse/cst.js 3.2 KB runs code
- vendor/yaml/dist/parse/lexer.js 24 KB runs code
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.
- 2mo ago First seen · 240 lines · 98 tokens per session scan A d65f1ea80525
rn-upgrade-pulse is a skill published in the GitHub repository AndrewDongminYoo/rn-agents-kit (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 98 tokens to every session and 7,115 once invoked, about $0.0004 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 2026-09-05.
rn-upgrade-pulse compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| rn-upgrade-pulseAndrewDongminYoo/rn-agents-kit | Skill | 3 | yesterday | Apache-2.0 | A | 98 | Claude Code |
| expoericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 79 | Claude Code, Codex |
| react-nativeericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 90 | Claude Code, Codex |
| init-projectwataru-maeda/react-native-boilerplate | Skill | 524 | 5d ago | MIT | A | 50 | Claude Code, Codex |
| validate-mobilejohnkozaris/jko-claude-plugins | Skill | 11 | yesterday | MIT | A | 20 | Claude Code |
| ccc-mobileKevinZai/commander | Skill | 6 | yesterday | MIT | A | 39 | Claude Code |
| swiftui-expertjohnkozaris/jko-claude-plugins | Skill | 11 | yesterday | MIT | A | 133 | Claude Code |