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/nweii/agent-stuff/tirith-confignpx skills add nweii/agent-stuff --skill tirith-configgit clone --depth 1 https://github.com/nweii/agent-stuffWrote 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/nweii/agent-stuff/tirith-config)<a href="https://agentmods.dev/skills/nweii/agent-stuff/tirith-config"><img src="https://agentmods.dev/badge/skills/nweii/agent-stuff/tirith-config.svg" alt="Measured on agentmods" 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 | $0.00069 | $0.01575 |
| Opus 5 | $0.00034 | $0.00788 |
| Sonnet 5 | $0.00014 | $0.00315 |
| Haiku 4.5 | $0.00007 | $0.00158 |
Grade B, and why
tirith-config scanned grade B 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 4d 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.
Downloads and executes remote codemediumSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
Tirith intercepts shell commands and pasted content to catch homograph URLs (Cyrillic lookalikes, mixed scripts), ANSI escape injection, and `curl | bash`–style pipe-to-shell patterns. This skill encodes operating proced Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Tirith intercepts shell commands and pasted content to catch homograph URLs (Cyrillic lookalikes, mixed scripts), ANSI escape injection, and `curl | bash`–style pipe-to-shell patterns. This skill encodes operating proced How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tirith-config
Tirith intercepts shell commands and pasted content to catch homograph URLs (Cyrillic lookalikes, mixed scripts), ANSI escape injection, and curl | bash–style pipe-to-shell patterns. This skill encodes operating procedure — decision logic, verification rituals, and inherent gotchas. The current allowlist and tool version are not encoded here; query them at runtime.
Operating model
Tirith has four moving parts. Treat the live config as source of truth, not memory:
- Shell hook — sourced via
eval "$(tirith init --shell zsh)"in the user's shell profile. This is what wires per-command interception. Hook source files at~/.local/share/tirith/shell/are inert until the eval line is added to the profile. - Policy file —
~/.config/tirith/policy.yaml(global) and.tirith/policy.yaml(per-project, walks up from cwd). The per-project file wins when present. - Audit log —
~/.local/share/tirith/log.jsonl. Redacted previews, not full commands. - Receipts — created by
tirith run <url>. Verifiable later withtirith receipt verify <sha256>.
tirith doctor is the canonical health check; it surfaces hook status, policy detection, and bypass mode in one shot.
Decision tree: a command was blocked
Three responses, each appropriate for a different shape of problem:
- Allowlist the hostname — only when the vendor is trusted and you'll pipe-shell from them repeatedly. Add to
allowlist:in~/.config/tirith/policy.yaml. Reserve for canonical installer domains (e.g.,get.docker.com,sh.rustup.rs). Allowlist only suppresses pipe-shell rules for that exact hostname; content-level checks (homograph, mixed-script, ANSI) still run. tirith run <url>— for one-off installs you want to inspect. Downloads to a temp file, shows SHA256, runs static analysis, opens in a pager for review, executes only after confirmation, and writes a receipt.TIRITH=0 <cmd>prefix — per-command bypass when you've already vetted the script elsewhere or are operating in a known-safe context. The variable only persists for that single command. Disabled ifallow_bypass: falsein policy.
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.
- 4d ago First seen · 111 lines · 69 tokens per session scan B 3db5baf6f89d
tirith-config is a skill published in the GitHub repository nweii/agent-stuff (8 stars, last pushed 16d ago), licensed MIT. It adds 69 tokens to every session and 1,575 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…