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/costWrote 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/cost)<a href="https://agentmods.dev/skills/sethgammon/citadel/cost"><img src="https://agentmods.dev/badge/skills/sethgammon/citadel/cost/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/cost"><img src="https://agentmods.dev/badge/skills/sethgammon/citadel/cost.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 114 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00046 | $0.01661 |
| Opus 5.5 | $0.00018 | $0.00664 |
| Sonnet 5.5 | $0.00009 | $0.00332 |
| Haiku 4.5 | $0.00005 | $0.00166 |
Grade A, and why
cost 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 1mo 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cost -- Session & Campaign Cost Explorer
When to Use
/cost-- current session cost and burn rate/cost today-- today's total spend/cost week-- this week's spend/cost campaign {slug}-- total spend for a specific campaign/cost all-- lifetime cost summary- When /do routes "how much", "what's the cost", "spending", "tokens", "burn rate"
Inputs
Optional arguments parsed from user message:
today-- filter to today's sessionsweek-- filter to last 7 dayscampaign {slug}-- filter to a specific campaignall-- show all-time data- No argument -- show current session
Protocol
Step 1: READ REAL DATA
Run the session-tokens.js script to get real token data:
node scripts/session-tokens.js # current/latest session
node scripts/session-tokens.js --today # today's sessions
node scripts/session-tokens.js --all # all sessions (use for week/all/campaign)
Also read:
.planning/telemetry/cost-tracker-state.jsonfor live burn rate.planning/telemetry/session-costs.jsonlfor campaign attributionscripts/pricing.jsonto show which pricing is being used
If session-tokens.js is not available or fails, fall back to session-costs.jsonl
data and clearly mark output as "(estimated)".
Step 2: RENDER BASED ON SCOPE
Current session (/cost with no args):
=== Session Cost Report ===
Session: {sessionId (first 8 chars)}
Started: {relative time} ({absolute time})
Duration: {minutes} min
Tokens:
Input: {N} tokens
Output: {N} tokens
Cache creation: {N} tokens
Cache read: {N} tokens
Total: {N} tokens
Cost: ${total}
Burn rate: ${rate}/min
Messages: {N} ({N} main + {N} across {N} subagents)
Model breakdown:
claude-opus-4-6: {N} messages (${cost}, {pct}% of spend)
claude-haiku-4-5: {N} messages (${cost}, {pct}% of spend)
Cache efficiency: {pct}% of input tokens served from cache
(Higher = more cost-efficient. Cache reads cost 10x less than fresh input.)
Pricing source: scripts/pricing.json (version {version})
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.
- 1mo ago First seen · 191 lines · 46 tokens per session scan A 2e50300c0e3f
cost is a skill published in the GitHub repository SethGammon/Citadel (925 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 1,661 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
finance
Runtime subject skill payload for finance subject activation.
business-model
Use when deciding or revisiting how the product makes money — pricing, tiers, trial shape, ad load, unit economics — by ceo when setting the model, by cpo when a scope decision turns on revenue, and by product-researcher when investigating willingness to pay. A pricing analysis is a document, not a standing role.
opendart-excel
A workflow for creating Excel files from South Korea’s DART company filings, which are public financial reports submitted to the Financial Supervisory Service.
signals-scout-revenue-analytics
Signals scout for PostHog revenue analytics. Watches for upstream failures (Stripe sync stalls, capture regressions), and config drift.
understanding-billing-usage
Explains PostHog billing usage and spend from the customer's visible Billing MCP tools. Use when the user asks why usage or spend is high, which product or project is driving usage, what a usage type means, how to reduce usage, what changed over time, why they got a usage change alert, or whether a spike/drop alert…
tokendiet
Audit this codebase for wasteful LLM API spend and hand back a concrete, honest fix plan — missing prompt caching, uncapped retries, prompt bloat, no batching, overpowered models. Describes technical waste and published provider rates only; never fabricates a dollar figure. Trigger on requests like "audit my LLM…