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 tellang/triflux --skill tfx-livegit clone --depth 1 https://github.com/tellang/trifluxWrote 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/tellang/triflux/tfx-live)<a href="https://agentmods.dev/skills/tellang/triflux/tfx-live"><img src="https://agentmods.dev/badge/skills/tellang/triflux/tfx-live/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/tellang/triflux/tfx-live"><img src="https://agentmods.dev/badge/skills/tellang/triflux/tfx-live.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 | $0.00053 | $0.01408 |
| Opus 5 | $0.00026 | $0.00704 |
| Sonnet 5 | $0.00011 | $0.00282 |
| Haiku 4.5 | $0.00005 | $0.00141 |
Grade A, and why
tfx-live scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tfx-live — Claude↔Codex live orchestration
tfx-live is the Triflux-owned live bridge for Claude Code and Codex TUI sessions.
It runs as a local CLI (tfx-live) and supports tmux TUI control plus Claude daemon UDS attach.
Default transport
- Claude targets with
--shortor--session-id: UDS-firstautoby default. - If UDS probe/attach fails: write
~/.claude/cache/triflux/tfx-live/bug-reports/uds-fallback-*.json, then tmux fallback when--sessionis provided. - Codex targets and Claude targets without a daemon ref: tmux by default.
- UDS completion contract:
done=trueonly whenmatchedCompletion===true;timedOutorclosedis not completion. - Bridge resolution:
--bridge>$TFX_BRIDGE>$TFX_REPO_ROOT/hub/bridge.mjs> bundled Trifluxhub/bridge.mjs.
Quick start
# Claude -> Codex helper session
tfx-live start --cli codex --session cx1 --cwd ~/Projects
tfx-live ask --cli codex --session cx1 --prompt "현재 변경사항을 요약해줘" --timeout 120
tfx-live stop --cli codex --session cx1
# Codex -> Claude tmux helper session
tfx-live start --cli claude --session cl1 --cwd ~/Projects
tfx-live ask --cli claude --session cl1 --prompt "이 구현을 리뷰해줘" --timeout 120
tfx-live stop --cli claude --session cl1
UDS-first Claude daemon ask
Find daemon sessions:
tfx-live probe
Then ask by short:
tfx-live ask --cli claude --short <8hex> --prompt "STRUCTURED_RETURN_OK 만 답해줘" --timeout 120
Because --short is present, the default transport is auto: probe UDS first, then tmux fallback only if --session is also provided.
For explicit UDS-only failure behavior:
tfx-live ask --cli claude --transport uds --short <8hex> --prompt "..." --timeout 120
Codex tmux session discovery
List the Codex CLI sessions already running in tmux; this does not require a
prior tfx-live start. The JSON result includes the tmux session name, start
time, current working directory, and attachment state.
# All locally running Codex tmux sessions
tfx-live list-sessions --cli codex
# Limit discovery to sessions whose pane cwd exactly matches this worktree
tfx-live list-sessions --cli codex --cwd ~/Projects/my-worktree
What ships with it
1 file 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.
- 9d ago First seen · 126 lines · 53 tokens per session scan A b3645c4eaeeb
tfx-live is a skill published in the GitHub repository tellang/triflux (7 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 1,408 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
lucia-chat
Set two agent sessions talking through the Luciazero Agent Bus and watch it live in a terminal: pick the pair, open the windows, read the transcript. Use for "ให้ codex กับ claude คุยกัน" or "watch the bus".
ready
Make an unfamiliar repository agent-ready with a verify command, smoke tests, guardrails, and project notes. Use for repository setup, agentic engineering, verify commands, hooks, or allowlists; skip when verification and scope are already clear.
handoff
Write a state capsule so the next session — or a different agent/harness — can resume unfinished work without re-deriving context. Use when a session is ending with work incomplete, when the user says "handoff", "pack up", "ส่งต่อ", "continue tomorrow", when switching between Claude Code and Codex mid-task, or when…
done
Run the closeout ritual before handing back non-trivial work; full verification, revert-probe honesty, independent review, and scope reporting. Use before declaring completion, opening a PR, wrapping up a change, or "ปิดงาน".
retro
Record durable lessons, null results, and footguns after hard work or debugging. Use when the user asks for a retro, dead ends need preserving, a task disproves an approach, or "จดบทเรียน". Keep repo knowledge separate from machine-local memory.
show
Visualize code structure, changes, and verification evidence in the smallest useful view. Use for connections, flows, diffs, file maps, Mermaid diagrams, evidence maps, or focused HTML; show facts and label unknowns.