Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/SethGammon/Citadelnpx agentmods add skills/sethgammon/citadel/ascii-diagramWrote 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/sethgammon/citadel/ascii-diagram)<a href="https://agentmods.dev/skills/sethgammon/citadel/ascii-diagram"><img src="https://agentmods.dev/badge/skills/sethgammon/citadel/ascii-diagram/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/sethgammon/citadel/ascii-diagram"><img src="https://agentmods.dev/badge/skills/sethgammon/citadel/ascii-diagram.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00043 | $0.02931 |
| Opus 5.5 | $0.00017 | $0.01172 |
| Sonnet 5.5 | $0.00009 | $0.00586 |
| Haiku 4.5 | $0.00004 | $0.00293 |
Grade A, and why
ascii-diagram 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 2mo 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 — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ascii-diagram — Perfectly Aligned ASCII Diagrams
Orientation
Use when:
- The user wants any kind of text/ASCII diagram: architecture, flow, sequence, box-and-arrow, tree, table, org chart, network topology
- A diagram needs to be embedded in markdown, code comments, or plain text
- Visual alignment matters
Do NOT use when:
- The user wants an image (suggest Mermaid, PlantUML, or an image tool instead)
- The diagram is trivial (a single box or a one-line arrow)
What this skill needs:
- A description of what to diagram
- Optional: preferred style (single-line
+--+, double-line╔══╗, rounded╭──╮, heavy┏━━┓) - Optional: target width constraint
Protocol
Step 1: PLAN THE LAYOUT
Before writing ANY characters, plan the diagram structurally:
- Identify elements: List every box/node and its label text
- Identify connections: List every arrow/line between elements, with optional labels
- Choose layout direction: left-to-right, top-to-bottom, or mixed
- Calculate dimensions:
- Each box width = max label line length + 4 (2 padding + 2 border)
- Each box height = label line count + 2 (top + bottom border)
- Gutters between boxes: minimum 3 characters for arrows (
→) - For vertical arrows: minimum 1 row gap
Write this plan out explicitly before proceeding. Example:
Elements:
A: "Client" → width=10, height=3
B: "Server" → width=10, height=3
C: "Database" → width=12, height=3
Layout: left-to-right
Connections: A→B (HTTP), B→C (SQL)
Total width: 10 + 6 + 10 + 6 + 12 = 44
Step 2: BUILD ON A CHARACTER GRID
Use this JavaScript approach mentally (or actually execute it via Bash if the diagram is complex):
// For complex diagrams, RUN this — don't try to hand-align
class Grid {
constructor(w, h) {
this.w = w; this.h = h;
this.cells = Array.from({length: h}, () => Array(w).fill(' '));
}
put(x, y, char) {
if (x >= 0 && x < this.w && y >= 0 && y < this.h) this.cells[y][x] = char;
}
text(x, y, str) {
for (let i = 0; i < str.length; i++) this.put(x + i, y, str[i]);
}
box(x, y, w, h, label) {
// Top border
this.put(x, y, '+');
for (let i = 1; i < w-1; i++) this.put(x+i, y, '-');
this.put(x+w-1, y, '+');
// Bottom border
this.put(x, y+h-1, '+');
for (let i = 1; i < w-1; i++) this.put(x+i, y+h-1, '-');
this.put(x+w-1, y+h-1, '+');
// Sides
for (let j = 1; j < h-1; j++) {
this.put(x, y+j, '|');
this.put(x+w-1, y+j, '|');
}
// Label (centered)
const lines = label.split('\n');
const startY = y + Math.floor((h - lines.length) / 2);
for (let li = 0; li < lines.length; li++) {
const line = lines[li];
const startX = x + Math.floor((w - line.length) / 2);
this.text(startX, startY + li, line);
}
}
hArrow(x1, x2, y, label) {
// Horizontal arrow from x1 to x2 at row y
const dir = x2 > x1 ? 1 : -1;
for (let x = x1; x !== x2; x += dir) this.put(x, y, '-');
this.put(x2, y, dir > 0 ? '>' : '<');
if (label) {
const lx = Math.min(x1, x2) + Math.floor((Math.abs(x2-x1) - label.length) / 2);
this.text(lx, y - 1, label);
}
}
vArrow(x, y1, y2, label) {
// Vertical arrow from y1 to y2 at column x
const dir = y2 > y1 ? 1 : -1;
for (let y = y1; y !== y2; y += dir) this.put(x, y, '|');
this.put(x, y2, dir > 0 ? 'v' : '^');
if (label) this.text(x + 2, Math.min(y1, y2) + Math.floor(Math.abs(y2-y1) / 2), label);
}
render() {
return this.cells.map(row => row.join('').trimEnd()).join('\n');
}
}
What ships with it
2 files 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.
- 2mo ago First seen · 301 lines · 43 tokens per session scan A 5f60084f1e0d
ascii-diagram is a skill published in the GitHub repository SethGammon/Citadel (927 stars, last pushed 2d ago), licensed MIT. It adds 43 tokens to every session and 2,931 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
compose-org
Run a task as an evolved multi-agent ORG using the installed liquid-org framework — where YOU (the running Claude) embody the org: you ask liquid-org which proven team topology + specialist personas to use (retrieved from its evolved pool, or assembled fresh), then dispatch ONE SUBAGENT PER TALENT to play each role…
liquid-rank
Rank the available skills by RELEVANCE to the current task, on demand, using liquid-org's read-only hermes skill ranker. This is an EXPLICIT, OPT-IN selector you invoke WHEN you want help choosing the most relevant skill for what you're doing — it is NOT default, automatic skill selection, and it does NOT decide for…
present-gate
First-officer gate-presentation rendering — the captain-facing gate-review template and assembly rules, including workflow-owned finding labels. Invoke at the gate point after the FO has decided a stage must be presented.
tmux-layout
Use this skill when the operator wants a prepared tmux visualization layout for the session's side-channels (STATE.md tail, CI-watch, events.jsonl tail). Renders a 4-pane default layout or debug layout. Read-only side-channel observability — the coordinator chat stays in the operator's original terminal. Trigger…
vault-mirror
Use when you need to populate the Meta-Vault with machine-generated notes derived from session-orchestrator JSONL records. Converts entries from .orchestrator/metrics/sessions.jsonl and .orchestrator/metrics/learnings.jsonl into vault-conformant Markdown under 50-sessions/ and 40-learnings/. Called automatically at…
prototype
Use when asked to prototype one design question through a cheap logic or UI experiment, including button-driven state-model checks. Not for polished artifacts: use polished-web-prototype.