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/send-feedbackgit 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 | $0.00039 | $0.02575 |
| Opus 5 | $0.00019 | $0.01288 |
| Sonnet 5 | $0.00008 | $0.00515 |
| Haiku 4.5 | $0.00004 | $0.00258 |
Grade A, and why
send-feedback 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 2d 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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Send Feedback — Sanitized Bug Report / Feature Request
Guide the user through submitting feedback for the rn-dev-agent plugin. All data is sanitized before submission — no home paths, secrets, PII, or IP addresses leave the local machine.
Step 0: Check for pre-written context
If $ARGUMENTS is provided, use it as the starting description. Scan the
argument text for clues about type (bug/feature/question), steps to reproduce,
workarounds, related issues, and suggested fixes. Pre-fill as much as
possible so the user only confirms rather than re-typing.
Step 1: Gather feedback details
Ask: "What would you like to report?"
- Bug report — something broken or unexpected
- Feature request — something missing or could be improved
- Question — need help understanding something
Then collect the following (skip what was already provided via $ARGUMENTS):
- Description (1-3 sentences) — what happened or what's needed
- Steps to reproduce (for bugs) — numbered list of steps. Ask: "How can I reproduce this?"
- Known workaround (optional) — "Did you find a workaround or fix?"
- Related issues (optional) — "Any related GitHub issues? (e.g., #22, #23)"
- Suggested fix (optional, for bugs) — "Do you know what should change?"
Step 2: Collect environment context (automated)
Call rn_session with action: "status" first. Its public authority projection
returns the exact session's opaque sessionId; retain it locally and pass it only to the
collector process as RN_DEV_AGENT_SESSION_ID; do not include the ID in the
preview or submission. This keeps feedback authority aligned after a handoff,
when multiple released sessions can share one worktree.
Run the collection script from the project root to gather sanitized environment data:
PLUGIN_ROOT="${RN_DEV_AGENT_CODEX_PLUGIN_ROOT:-${CODEX_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-}}}"
PROJECT_ROOT="${RN_PROJECT_ROOT:-${CLAUDE_USER_CWD:-$PWD}}"
if [ -z "$PLUGIN_ROOT" ] && [ -f "packages/codex-plugin/.codex-plugin/plugin.json" ]; then
PLUGIN_ROOT="packages/codex-plugin"
fi
if [ -z "$PLUGIN_ROOT" ]; then
PLUGIN_MANIFEST="$(find "${CODEX_HOME:-$HOME/.codex}/plugins/cache" -path "*/rn-dev-agent/*/.codex-plugin/plugin.json" 2>/dev/null | sort -V | tail -n 1)"
[ -n "$PLUGIN_MANIFEST" ] && PLUGIN_ROOT="$(dirname "$(dirname "$PLUGIN_MANIFEST")")"
fi
if [ -n "$PLUGIN_ROOT" ] && [ -x "$PLUGIN_ROOT/scripts/collect-feedback.sh" ]; then
(cd "$PROJECT_ROOT" && RN_DEV_AGENT_SESSION_ID="<exact rn_session sessionId>" \
"$PLUGIN_ROOT/scripts/collect-feedback.sh")
elif command -v rn-collect-feedback >/dev/null 2>&1; then
(cd "$PROJECT_ROOT" && RN_DEV_AGENT_SESSION_ID="<exact rn_session sessionId>" \
rn-collect-feedback)
else
echo "rn-dev-agent feedback collector is missing; reinstall or update the plugin" >&2
exit 1
fi
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.
- 2d ago First seen · 258 lines · 39 tokens per session scan A c25bcc5bfe4f
send-feedback is a command published in the GitHub repository Lykhoyda/rn-dev-agent (11 stars, last pushed 2d ago), licensed MIT. It adds 39 tokens to every session and 2,575 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.