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 commands/lykhoyda/rn-dev-agent/run-workflowgit clone --depth 1 https://github.com/Lykhoyda/rn-dev-agentWhat 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 | $0.00049 | $0.00334 |
| Opus 5 | $0.00024 | $0.00167 |
| Sonnet 5 | $0.00010 | $0.00067 |
| Haiku 4.5 | $0.00005 | $0.00033 |
Grade A, and why
run-workflow 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.
What it actually says
Establish the proven operating sequence for this journey: $ARGUMENTS
Load the rn-workflow skill and execute its contract steps 0–7 in order, with
the journey description above as the scope for Step 5 ("run only the requested
proof"). If no description was given, ask for one before Step 5 — Steps 0–4
(validation and authority establishment) may proceed without it.
Ground rules the skill enforces (do not restate or reinterpret them here):
rn_session(action="status")is the sole classifier for a blocked session; follow only itsrecoveryRequirement.nextAction, re-read status after every recovery action, and stop after one bounded retry on an identical projection.- Action discovery is read-only; replay only via
cdp_run_actionafter device, Metro, and runner authority are proven. - Success is re-read from authoritative tool state, never exit codes or prose.
- Cleanup runs in reverse order and is verified by the postflight checker.
Report the outcome as a short table: one row per contract step with its readback evidence, plus the single actionable stop if the journey could not proceed.
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 · 28 lines · 49 tokens per session scan A a546cd315724
run-workflow is a command published in the GitHub repository Lykhoyda/rn-dev-agent (11 stars, last pushed 3d ago), licensed MIT. It adds 49 tokens to every session and 334 once invoked, about $0.0002 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 commands, from other repositories
dashboard-flow-auto
Toggle autonomous mode for a session's flow. Usage /dashboard:flow-auto.
dashboard-flow-abort
Abort the running flow on a session. Usage /dashboard:flow-abort.
dashboard-git-branches
List git branches for the current dir (current marked ). Runs locally, no LLM.
brainstorm
Command dispatcher for brainstorm.
discover
Command dispatcher for discover.
propose
Command dispatcher for propose.