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-harnessgit 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-harness)<a href="https://agentmods.dev/skills/tellang/triflux/tfx-harness"><img src="https://agentmods.dev/badge/skills/tellang/triflux/tfx-harness/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-harness"><img src="https://agentmods.dev/badge/skills/tellang/triflux/tfx-harness.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 | $0.00033 | $0.00654 |
| Opus 5 | $0.00016 | $0.00327 |
| Sonnet 5 | $0.00007 | $0.00131 |
| Haiku 4.5 | $0.00003 | $0.00065 |
Grade A, and why
tfx-harness 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 10d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tfx-harness — Codex adapter
This skill is a routing adapter, not an execution engine. Read D0–D11 from the canonical routing SSOT, classify the user intent against available host capability evidence, and return one immediate owner. Do not copy the routing tree, keyword rules, or owner matrix into this file.
Locate the routing SSOT
This skill is installed globally but the SSOT belongs to the Triflux project. Try these locations in order and return blocked only when all three fail:
$TFX_ROUTING_SSOT, when set..claude/rules/tfx-routing.mdbelow the main Git worktree, derived from the parent ofgit rev-parse --git-common-dir.- Walk upward from the current working directory looking for
.claude/rules/tfx-routing.md.
Do not use git rev-parse --show-toplevel for step 2. In a linked worktree it
returns that worktree root, whose SSOT may be a stale branch snapshot.
--git-common-dir still points to the main repository's .git directory.
When blocked, include this one-line remedy:
export TFX_ROUTING_SSOT=<triflux clone>/.claude/rules/tfx-routing.md
Prefer ~/.zshenv for this variable because hooks and headless workers may not
load interactive ~/.zshrc. Do not create a global copy or symlink under
~/.claude/rules/; Claude auto-loads that directory into unrelated sessions.
Return contract
Translate only host syntax. Hook-injected routing context is authoritative for
the current turn. Resolve the SSOT owner against the current Codex Available
Skills inventory, preserving the exact $skill name when it exists.
[tfx-harness]
branch: D<n>
owner: <exactly one immediate owner>
availability: available | unavailable | unknown
fallback_notice: <optional>
status: recommendation-only | dispatching | blocked
- Return exactly one branch and one immediate owner.
- With unknown availability, do not infer a fallback.
- With measured unavailability, report
owner unavailable → tfx-X fallbackbefore using the fallback. - If the SSOT cannot be read, return
blocked: routing SSOT unavailableand the remedy above. - For a “which skill/path?” question, remain recommendation-only.
- When the user clearly requests execution, read the selected downstream
SKILL.md, invoke or follow that exact Codex$skill, and then relinquish routing ownership. Do not keep solving the downstream task inside this adapter once its owner is available. - If the owner is unavailable, use only the fallback explicitly allowed by the SSOT and label the measured unavailability before dispatch.
- Do not select downstream implementation agents, models, profiles, or effort.
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.
- 10d ago First seen · 67 lines · 33 tokens per session scan A bc7bf74c87fe
tfx-harness is a skill published in the GitHub repository tellang/triflux (7 stars, last pushed 2d ago), licensed MIT. It adds 33 tokens to every session and 654 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 2026-08-31.
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.