Borrowing it
Nothing to install: this file belongs to georgeturneruk/tckit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/georgeturneruk/tckit/main/.claude/skills/tc-config/SKILL.mdgit clone --depth 1 https://github.com/georgeturneruk/tckitWrote 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/georgeturneruk/tckit/tc-config)<a href="https://agentmods.dev/skills/georgeturneruk/tckit/tc-config"><img src="https://agentmods.dev/badge/skills/georgeturneruk/tckit/tc-config/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/georgeturneruk/tckit/tc-config"><img src="https://agentmods.dev/badge/skills/georgeturneruk/tckit/tc-config.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 | $0.00160 | $0.01623 |
| Opus 5 | $0.00080 | $0.00812 |
| Sonnet 5 | $0.00032 | $0.00325 |
| Haiku 4.5 | $0.00016 | $0.00162 |
Grade A, and why
tc-config 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configuring TcKit
TcKit's configuration surface is the safety stance: one JSON file at ~/.tckit/permissions.json (or $TCKIT_HOME/permissions.json). The server hot-reloads it on every tool call, so a change (a SetPermissions call or a hand edit) takes effect on the next call with no reconnect. The old Python CLI (tckit init / tckit config / tckit doctor) and ~/.tckit/config.toml are retired; if the user reaches for one of those, drive the flows below instead.
The two axes
Mode is a tier: read < write < execute.
read: inspect only (project reads, doc lookups).write: also author the project on disk (add/update POUs, GVLs, DUTs).execute: also act on a live target. Execute-class tools are exactly the NetId-gated set: Deploy, StartRuntime, RunTests, WriteSymbols, InvokeRpc.
A call above the current mode returns {"error": "Permission denied: ..."} naming the missing mode.
Target NetIds gate execute-class calls by target:
blocked_net_ids: NetIds that can never be acted on from this machine. Block always wins over the allowlist.allowed_net_ids: if non-empty, execute-class calls are permitted only against these NetIds. Empty means any non-blocked target.
The two tools
GetPermissions(): show the current stance (mode plus both NetId lists). Callable in any mode.SetPermissions(mode, allowedNetIds, blockNetIds): change the stance and persist it (creates the file on first use). Callable in any mode. Argument semantics:mode:read|write|execute; empty leaves it unchanged.allowedNetIds: comma-separated list that replaces the allowlist; empty leaves it unchanged; the literalnoneclears it (any non-blocked target allowed).blockNetIds: comma-separated list appended toblocked_net_ids. This tool can never remove a blocked NetId; unblocking happens only by editing the file.
Failure stances (how the gate reads an odd file)
- Missing file: permissive (
execute, no NetId restrictions). The stance is opt-in. - Unparseable file: keep the last good settings rather than bricking the server or silently widening.
- Valid file with an unrecognised
modevalue: fall toread(a present-but-typo'd mode signals an intent to restrict). - Valid file with the
modekey absent:execute(unrestricted).
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 · 88 lines · 160 tokens per session scan A 7580b01703d0
tc-config is a skill published in the GitHub repository georgeturneruk/tckit (5 stars, last pushed 16d ago), licensed MIT. It adds 160 tokens to every session and 1,623 once invoked, about $0.0008 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
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.