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/reflexioai/claude-smart/run-servicesnpx skills add ReflexioAI/claude-smart --skill run-servicesgit clone --depth 1 https://github.com/ReflexioAI/claude-smartWhat 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 | $0.00038 | $0.02353 |
| Opus 5 | $0.00019 | $0.01177 |
| Sonnet 5 | $0.00008 | $0.00471 |
| Haiku 4.5 | $0.00004 | $0.00235 |
Grade C, and why
run-services scanned grade C with 2 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf reflexio/website/.next reflexio/public_docs/.next Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Check each service individually. Use `curl --max-time 10 -s -o /dev/null -w "%{http_code}"` to get HTTP status codes. Copies of this mod
1 near-identical copy found in the catalogue:
- run-services — 92% identical, 14 lines differ
How it starts
The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run Services
Start all local development services with pre-flight dependency checks and automatic error recovery.
Overview
This command automates the full startup workflow: 0. Smart port selection — auto-detects free port group or reuses current worktree's ports
- Pre-flight dependency checks (uv sync, venv, npm, worktree editable packages)
- Stops any existing services (only if needed)
- Starts all services via
run_services.sh - Health-checks each service
- Diagnoses and fixes failures, then retries (up to 2 retries)
Port Configuration
Ports are allocated in groups of 3 with a +10 offset between groups:
| Group | Frontend | Backend | Docs |
|---|---|---|---|
| Default | 8080 | 8081 | 8082 |
| +10 | 8090 | 8091 | 8092 |
| +20 | 8100 | 8101 | 8102 |
| +30 | 8110 | 8111 | 8112 |
| +40 | 8120 | 8121 | 8122 |
| Service | Env Var | Base Port |
|---|---|---|
| Frontend (Next.js) | FRONTEND_PORT |
8080 |
| Backend (FastAPI) | BACKEND_PORT |
8081 |
| Docs (Fumadocs) | DOCS_PORT |
8082 |
| Step 0 (Smart Port Selection) determines which group to use automatically, unless ports are already set via environment variables. |
Execution Steps
Step 0: Smart Port Selection
Pre-check: If BACKEND_PORT, FRONTEND_PORT, or DOCS_PORT are already set in the environment, skip auto-detection entirely and use those values directly. Report "Using pre-configured ports" and proceed to Step 1.
0.1 Get current worktree root:
WORKTREE_ROOT=$(git rev-parse --show-toplevel)
0.2 For each port group (offset 0, 10, 20, 30, 40 — max 5 attempts), check all 3 ports in the group. For each port, determine its status:
PID=$(lsof -t -i:$PORT 2>/dev/null | head -1)
If no PID → port is free.
If PID exists, get the process's working directory:
PROC_CWD=$(lsof -a -p $PID -d cwd -Fn 2>/dev/null | tail -1 | sed 's/^n//')
Then classify:
- own —
$PROC_CWDstarts with$WORKTREE_ROOT(use prefix match, since child processes like Next.js run from subdirectories like$WORKTREE_ROOT/reflexio/website) - other —
$PROC_CWDdoes NOT start with$WORKTREE_ROOT
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 · 248 lines · 38 tokens per session scan C aeaa65a8a33a
run-services is a skill published in the GitHub repository ReflexioAI/claude-smart (774 stars, last pushed 3d ago), licensed Apache-2.0. It adds 38 tokens to every session and 2,353 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
reflexio-embedded
Captures user facts and procedural corrections into .reflexio/ so the agent learns across sessions. Use when: (1) user states a preference, fact, config, or constraint; (2) user corrects the agent and confirms the fix with an explicit 'good'/'perfect' or by moving on without re-correcting for 1-2 turns; (3) at start…
reflexio-consolidate
Run a full-sweep consolidation over all .reflexio/ files — TTL sweep + n-way cluster merge. Use when the user asks to 'clean up reflexio', 'consolidate memory', 'deduplicate playbooks', or suspects drift across sessions.
reflexio
When to use: Always active. This skill is the contract between you and the reflexio cross-session memory plugin.
learn
When to use: The user wants immediate extraction of skills/preferences from the current session — e.g., after a major correction, before context compaction, or to test the loop.
clear-all
When to use: The user explicitly asks to delete all locally-stored skills/preferences. This is destructive and unrecoverable.
show
When to use: The user wants to see what reflexio currently knows about this project.