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.
git clone --depth 1 https://github.com/Mark393295827/third-brain-v7-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/commands/mark393295827/third-brain-v7-skills/token-cost-tracker)<a href="https://agentmods.dev/commands/mark393295827/third-brain-v7-skills/token-cost-tracker"><img src="https://agentmods.dev/badge/commands/mark393295827/third-brain-v7-skills/token-cost-tracker/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/commands/mark393295827/third-brain-v7-skills/token-cost-tracker"><img src="https://agentmods.dev/badge/commands/mark393295827/third-brain-v7-skills/token-cost-tracker.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 | $0.00028 | $0.00587 |
| Opus 5.5 | $0.00011 | $0.00235 |
| Sonnet 5.5 | $0.00006 | $0.00117 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
token-cost-tracker 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Token Cost Tracker
This is a utility command, not an Agent Skill. Pricing and model catalogs change; obtain rates from the current runtime/provider billing source and record its timestamp.
Inputs
task: ""
model_id: "runtime identifier"
capability_class: fast | reasoning | multimodal | evaluator | other
input_tokens: 0
cached_input_tokens: 0
output_tokens: 0
rates_per_million:
input: null
cached_input: null
output: null
currency: ""
rate_source: ""
rate_checked_at: ""
If rates are unavailable, return token totals and cost_status: unknown; do not guess a price.
Estimate
Use measured source size, a comparable prior run, or an explicit low/base/high token range. Calculate each scenario:
cost = (input_tokens / 1,000,000 * input_rate)
+ (cached_input_tokens / 1,000,000 * cached_input_rate)
+ (output_tokens / 1,000,000 * output_rate)
Report assumptions, rate source/age, and the budget stop threshold. Do not infer token count from pages without labeling the conversion assumption.
Log
Append actual usage to .token-log.csv:
date,task,model_id,capability_class,input_tokens,cached_input_tokens,output_tokens,input_rate,cached_input_rate,output_rate,currency,cost,rate_source,notes
2026-07-11,wiki-ingest,runtime-model,reasoning,45231,12000,8732,0,0,0,USD,,provider-billing-page,rate unavailable at log time
Never rewrite historical rates. A later reconciliation appends a correction row referencing the original record.
Report
For the requested period return:
- input, cached-input, output, and total tokens;
- known cost by currency (never combine currencies silently);
- unknown-cost rows requiring reconciliation;
- breakdown by task, capability class, and model id;
- estimate-versus-actual error when estimates exist;
- largest cost driver and one bounded optimization test.
Failure Rules
- Missing token counts: return
NEEDS_INPUT. - Missing rates: compute usage only and mark cost unknown.
- Stale rates: use only when the user accepts the dated estimate; otherwise refresh.
- Mixed currencies: report separately or convert with an explicit dated exchange rate.
- Log path not writable: return
BLOCKED_PERMISSION; do not claim the row was saved.
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 · 74 lines · 28 tokens per session scan A d1c754726555
token-cost-tracker is a command published in the GitHub repository Mark393295827/third-brain-v7-skills (141 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 587 once invoked, about $0.0001 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 commands, from other repositories
okf
A command that exports a private knowledge wiki into an OKF-compatible bundle. OKF is a format for packaging knowledge, with a separate guarded mode for preparing material to share externally.
setup
Configure Vault PKM plugin — set vault path, API keys, and verify setup.
decompose
Feature/story breakdown — consume a ready-for-decompose scope doc and produce a task graph in the issue tracker. Re-entrant; tracker-as-canonical with vault breadcrumb.
sol
Run a one-shot task on the routed Codex model (gpt-5.6-sol by default) and relay its answer.
pdf-to-wiki
A workflow for sending a large PDF from Google Drive to NotebookLM, Google's document-analysis tool, and saving the resulting notes as Obsidian markdown files. It passes the file link rather than reading the PDF directly.
dossier
Force load of Dossier vault profile (and inbox check) before processing the rest of the user's request.