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 jamestexas/agents --skill hudgit clone --depth 1 https://github.com/jamestexas/agentsWrote 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/jamestexas/agents/hud)<a href="https://agentmods.dev/skills/jamestexas/agents/hud"><img src="https://agentmods.dev/badge/skills/jamestexas/agents/hud/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/jamestexas/agents/hud"><img src="https://agentmods.dev/badge/skills/jamestexas/agents/hud.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 | $0.00098 | $0.03660 |
| Opus 5.5 | $0.00039 | $0.01464 |
| Sonnet 5.5 | $0.00020 | $0.00732 |
| Haiku 4.5 | $0.00010 | $0.00366 |
Grade A, and why
hud 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 23d 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 — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hud — authoring skill for the personal work HUD
The HUD is a folder of markdown at $HUD_ROOT (env var, default ~/hud).
It is not a tool you call — it is a place you write files, in a shape a
small local server can render. This skill is the shape.
0. Resolve the root
Use $HUD_ROOT if set, else ~/hud. If that directory does not exist,
stop and say so — do not create it. The HUD root is scaffolded once by
its own setup step; a skill invocation is never the place that happens.
1. Load the schema file first
Before writing anything, check for $HUD_ROOT/HUD.md. If it exists, read
it — it is the schema file, co-owned by the user and every agent that
writes here, and it wins over this skill on any conflict (a path,
frontmatter field, or convention it states supersedes what's written
below). If it doesn't exist, proceed on the conventions in this file.
2. Figure out what's being asked for
The table below is generated from _hud/hud-contract.mjs, the one file
that declares what an entry is. Don't hand-edit it — hud docgen --check
fails when it drifts, and the unit suite runs that check.
| Intent | Kind | Target |
|---|---|---|
| capture a note | note |
$HUD_ROOT/projects/<project>/notes/<date>-<slug>.md |
| capture an unfiled note | inbox |
$HUD_ROOT/inbox/<date>-<slug>.md |
| capture a playbook | playbook |
$HUD_ROOT/playbooks/<slug>.md |
| create a project brief | context |
$HUD_ROOT/projects/<project>/CONTEXT.md |
| add a peer | peer |
$HUD_ROOT/peers/<handle>.md |
| drop raw material in | raw |
$HUD_ROOT/projects/<project>/raw/<date>-<slug>.<ext> |
Invoked with lint, run the lint workflow (§8) instead — no file writes
without approval.
Infer <project> from the current working directory's repo name, the
conversation's stated project, or an existing $HUD_ROOT/projects/<x>/
directory that matches. If none of those resolve it confidently, don't
guess — file under inbox/ instead. A note in the wrong project is worse
than a note that's unsorted; inbox/ is designed for exactly this.
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.
- 23d ago Changed · +83 lines f7b462c5a1a9
- 1mo ago First seen · 182 lines · 98 tokens per session scan A c214c6bffe9c
hud is a skill published in the GitHub repository jamestexas/agents (2 stars, last pushed 23d ago), licensed Apache-2.0. It adds 98 tokens to every session and 3,660 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-12.
Other skills, from other repositories
[object Object]
Read, search, and open notes in the user's "{{GRAPHNAME}}" Reflect graph via the reflect CLI. Use when the user asks about their notes, daily notes, journal, or anything they may have written down in Reflect.
okf
Author, maintain, and consume Open Knowledge Format (OKF) knowledge bundles — portable markdown + YAML frontmatter that both humans and agents read. Use when capturing project knowledge (services, APIs, schemas, metrics, runbooks, decisions) into an OKF bundle, when updating one after code or docs change, or when a…
catchup
Rebuild the human's lost context on a project from live state, in plain language: what needs them, what changed, what new words mean. Use when the human returns after a gap, says they can't follow the project anymore, asks what happened or what a term means, or before deciding what to do next when their mental model…
ralph-memory
Manage Al semantic memory entries — list, query, and clear lessons learned across loop iterations.
distill-feedback
A process for turning corrections you give an agent into lasting working rules. It reviews saved conversations and asks for approval before changing those rules.
ori-memory
Persistent agent memory with learning retrieval. Knowledge graph on markdown files — capture insights, decisions, research, and learnings during work, then retrieve them weeks or months later. Use when knowledge is too valuable to lose but too much to inject into every prompt.