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/lykhoyda/rn-dev-agent/creating-actionsnpx skills add Lykhoyda/rn-dev-agent --skill creating-actionsgit clone --depth 1 https://github.com/Lykhoyda/rn-dev-agentWrote 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/lykhoyda/rn-dev-agent/creating-actions)<a href="https://agentmods.dev/skills/lykhoyda/rn-dev-agent/creating-actions"><img src="https://agentmods.dev/badge/skills/lykhoyda/rn-dev-agent/creating-actions.svg" alt="Measured on agentmods" 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 | $0.00127 | $0.03540 |
| Opus 5 | $0.00063 | $0.01770 |
| Sonnet 5 | $0.00025 | $0.00708 |
| Haiku 4.5 | $0.00013 | $0.00354 |
Grade A, and why
creating-actions 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 3d 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
creating-actions — Author a Reusable Maestro Action
An action is a parameterised Maestro flow at <project>/.rn-agent/actions/<id>.yaml with an M7 metadata header, replayable via /rn-dev-agent:run-action or cdp_run_action (auto-repair-aware). A well-authored action turns a ~minutes interactive walk into a ~seconds deterministic replay. Authoring one well means: dedup first, ground every selector in evidence, design the flow as an ASCII diagram before writing YAML, validate, then replay to promote.
When to Use
- A verified flow is worth replaying: login, navigation prologue, multi-step setup, locale/theme switching, data seeding.
/rn-dev-agent:test-featureverification passed and the walk should be persisted.- The user asks to make a flow replayable / save an action.
When NOT to author an action:
- A one-off check — use
maestro_runwithinlineYamland throw it away. - An existing action already covers the flow — extend or parameterise it instead of forking a near-duplicate.
- The flow spans two apps — actions are single-
appIdby contract.
Step 0 — Scan the Inventory First (dedup)
Before authoring anything, check what already exists:
node "${CLAUDE_PLUGIN_ROOT}/rn-dev-agent-core/dist/learned-actions.js" --json --section b \
--workspace-root "$PWD" --memory-cwd "$PWD" --filter <keyword>
(or /rn-dev-agent:list-learned-actions <keyword>). Listing is read-only and grants no replay authority: if a match covers the goal, run the Step 6 ownership pre-flight first — call rn_session({action: "status"}), and if state is blocked, stop and follow recoveryRequirement.nextAction verbatim instead of replaying. Only then replay the match. If a near-match exists (same flow, hardcoded values), parameterise THAT action with ${VAR} placeholders rather than creating a sibling — duplicate actions rot independently and split the repair history.
Step 1 — Pick the Creation Path
| Situation | Path |
|---|---|
| About to walk the flow live on a device anyway | Recorder: cdp_record_test_start → drive UI (cdp_interact / device_*) → cdp_record_test_stop → cdp_record_test_save_as_action (writes header + sidecar; pass intent/tags/mutates/produces yourself — the recorder cannot infer them) |
| Flow and selectors already known (prior exploration, existing test) | Direct authoring — Steps 2–6 below |
| Structured steps in hand, want generated YAML | maestro_generate — then verify the M7 header per Step 4 and continue with Steps 5–6 |
What ships with it
2 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.
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.
- 3d ago First seen · 218 lines · 127 tokens per session scan A ae277b1abd1b
creating-actions is a skill published in the GitHub repository Lykhoyda/rn-dev-agent (11 stars, last pushed yesterday), licensed MIT. It adds 127 tokens to every session and 3,540 once invoked, about $0.0006 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
kungfu-agent-onboarding
Discover the exact Kungfu Project, WorkConsole, WorkRef, Skill catalog, and Core Work state admitted to this Amp process.
kungfu-agent-onboarding
Use when a user asks to understand, start, inspect, extend, or safely operate installed Kungfu; verify the installed pack, select one intent route, personalize the explanation, and propose one smallest safe next action.
minimal
Help an agent inspect a failed trace run, identify likely failure layers, and produce a short audit note.
company-product-context
Compiles comprehensive company product context from PDF documents, web research, and industry knowledge.
codebase-context-extractor
This skill provides a comprehensive context extraction system for large codebases. It intelligently analyzes code structure, dependencies, and relationships to extract relevant context for understanding, debugging, or modifying code.
deep-researcher
Performs comprehensive, multi-layered research on any topic with structured analysis and synthesis of information from multiple sources.