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/flurdy/agent-skills/token-dashboardnpx skills add flurdy/agent-skills --skill token-dashboardgit clone --depth 1 https://github.com/flurdy/agent-skillsWrote 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/flurdy/agent-skills/token-dashboard)<a href="https://agentmods.dev/skills/flurdy/agent-skills/token-dashboard"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/token-dashboard.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 5.1 | $0.00029 | $0.01578 |
| Opus 5 | $0.00015 | $0.00789 |
| Sonnet 5 | $0.00006 | $0.00316 |
| Haiku 4.5 | $0.00003 | $0.00158 |
Grade A, and why
token-dashboard 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 5d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Token Dashboard
Show read-only token telemetry for the current session and current UTC calendar week. The week starts
Monday at 00:00 UTC. This skill has no /usage alias and does not modify transcripts or settings.
Usage
/token-dashboard # terminal dashboard; optional OpenRouter analytics when configured
/token-dashboard --offline # local telemetry only; guarantees no network
/token-dashboard --json # normalized schema v1 JSON
/token-dashboard --json --offline # machine-readable local-only report
/token-dashboard --session-id ID # explicitly select a known local session; the ID is never emitted
Resolve scripts/token_dashboard.py relative to this SKILL.md, then run the executable with the
user's arguments. Pi can load the managed Claude/Codex skill directory through its configured skills
path, and the collector remains compatible with Pi telemetry:
/path/to/token-dashboard/scripts/token_dashboard.py --offline
/path/to/token-dashboard/scripts/token_dashboard.py --json
Do not replace the collector with ad-hoc transcript reads or provider calls. Never call this skill
/usage.
Output contract
The final response must paste the collector's complete stdout verbatim in a fenced code block.
Do this even when the Bash tool card already contains the same output or Pi collapses earlier lines.
Do not summarize, paraphrase, reformat, truncate, or replace stdout with a success message. Preserve
all Current session, Week, and Sources rows, including unavailable and partial diagnostics.
Use a json fence for --json and a plain-text fence otherwise. Do not alter the block itself.
Analysis contract
After the verbatim block, add an Analysis section of two to four concise bullets (at most 120 words total):
- summarize current-session requests and recorded total; when both counters are available, identify cache-read share as telemetry rather than cost;
- identify the largest week-to-date rows whose
totalis available, without treating rows with an unavailable total as zero; - explain partial, estimated, or unavailable data using the reported source diagnostics; and
- mention one actionable setup issue, such as a missing OpenRouter management key, only when present.
What ships with it
3 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.
- 5d ago First seen · 141 lines · 29 tokens per session scan A 4b846b2dddf5
token-dashboard is a skill published in the GitHub repository flurdy/agent-skills (8 stars, last pushed 7d ago), licensed MIT. It adds 29 tokens to every session and 1,578 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
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…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
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…