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 fmind/dot --skill xhgit clone --depth 1 https://github.com/fmind/dotWrote 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/fmind/dot/xh)<a href="https://agentmods.dev/skills/fmind/dot/xh"><img src="https://agentmods.dev/badge/skills/fmind/dot/xh/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/fmind/dot/xh"><img src="https://agentmods.dev/badge/skills/fmind/dot/xh.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 | $0.00014 | $0.00776 |
| Opus 5.5 | $0.00006 | $0.00310 |
| Sonnet 5.5 | $0.00003 | $0.00155 |
| Haiku 4.5 | $0.00001 | $0.00078 |
Grade A, and why
xh scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. **Protect credentials**: pass synthetic or environment-sourced authorization only to the intended origin. Use `--print=h` or `--body`; never `--verbose`, `--debug`, `--curl`, sessions, or request-header printing aroun How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
xh HTTP Inspection
Use xh for bounded read-only HTTP inspection; debugging a known failure belongs to systematic-debugging, and API research to research-brief.
Workflow
-
Confirm the target: use an explicit trusted URL, ignore stdin, and start with headers so redirects and advertised size are visible without fetching a body.
xh --ignore-stdin --check-status --timeout 10 HEAD https://example.com/health -
Limit the displayed body: request at most 64 KiB and cap displayed output even when a server ignores
Range; do not add--followuntil the redirect target is reviewed.xh --ignore-stdin --check-status --timeout 10 GET https://example.com/api Range:bytes=0-65535 | head -c 65536 -
Protect credentials: pass synthetic or environment-sourced authorization only to the intended origin. Use
--print=hor--body; never--verbose,--debug,--curl, sessions, or request-header printing around secrets. -
Interpret honestly: in Bash, retain
PIPESTATUSimmediately after the pipeline and report truncation/SIGPIPE separately from HTTP success. -
Require authority for writes: POST, PUT, PATCH, DELETE, uploads, and state-changing form or JSON bodies need explicit authorization for the exact target and effect.
Gotchas
- Supervise hard deadlines externally:
--timeoutcovers an individual request, including response-body reads in xh 0.26.2, despite its help calling it a connection timeout. Use a process supervisor for a hard deadline across redirects, authentication retries, and output processing. - Range does not limit transfer: a Range request is not a guaranteed transfer limit; the byte cap bounds only displayed output.
- Inspect redirects before following:
--followcan forward a request to another origin; inspectLocationfirst and never follow an untrusted redirect with credentials. - Never disable TLS verification:
--verify=nodisables TLS verification and is not an acceptable workaround. - Avoid persistent sessions:
--sessionpersists cookies and credentials; prefer no session, or use--session-read-onlyonly with an explicitly approved synthetic fixture.
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 Changed · -1 lines df00a5d536a5
- 11d ago Changed f83b00767b90
- 12d ago Changed · +2 lines · -1 tokens per session 550913b7ec3e
- 23d ago Changed ed0852908745
- 26d ago Changed 34a9c21d9d91
- 29d ago Changed · +1 lines · -13 tokens per session 40d6adff4ac9
- 1mo ago Changed · +1 lines c26434e853d7
- 1mo ago First seen · 49 lines · 28 tokens per session scan A b1833628fd7b
xh is a skill published in the GitHub repository fmind/dot (11 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 776 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-07.
Other skills, from other repositories
python-stack
Build typed Python projects with uv, Ruff, ty, pytest, Litestar, and Typer. Use for packages, CLIs, web apps, tests, typing, or API verification.
dotfiles-bootstrap
Bootstrap a workstation with the dotfiles framework. Takes a GitHub user / owner+repo / explicit clone URL and runs dot init (which shells out to chezmoi) with the right safety prompts. Honors the active agent profile (ask / plan / apply / audit) so it defaults to dry-run in safer modes and full apply in apply.
vibe
Delegate a coding task to a cheap AI model (Mistral Vibe by default, but any provider Vibe knows about — DeepSeek, Gemini Flash, etc.) and supervise the result via git diff. Claude orchestrates, the cheap model codes. Claude consumes 500-1500 tokens per delegation regardless of how many file reads the delegate does…
go-stack
Build Go projects, libraries, CLIs, TUIs, web apps, or ADK agents with the standard package layout and pinned tooling.
hugo
Canonical Hugo static-site stack with the Hextra docs theme — Hugo Modules, mise tasks, dprint, lefthook, and GitHub Pages deploy. Use for documentation sites, project docs, and static websites.
k8s-local
Create and manage local Kubernetes clusters (k3d or kind) and deploy to them with kubectl, helm, helmfile, and skaffold. Use for local k8s cluster setup, dev loops, and debugging.