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 gustavo-meilus/superpipelines --skill tokenizer-protocolgit clone --depth 1 https://github.com/gustavo-meilus/superpipelinesWrote 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/gustavo-meilus/superpipelines/tokenizer-protocol)<a href="https://agentmods.dev/skills/gustavo-meilus/superpipelines/tokenizer-protocol"><img src="https://agentmods.dev/badge/skills/gustavo-meilus/superpipelines/tokenizer-protocol.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 | $0.00043 | $0.01469 |
| Opus 5 | $0.00022 | $0.00734 |
| Sonnet 5 | $0.00009 | $0.00294 |
| Haiku 4.5 | $0.00004 | $0.00147 |
Grade A, and why
tokenizer-protocol 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 7d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tokenizer — Operational Protocol
Protocol
1. DISCOVER
- Read inputs from the orchestrator execution context:
input_path: path to the input markdown file to read.counts_output_path: path wherefrequency-counts.jsonmust be written.state_path: path topipeline-state.jsonfor status updates.run_id: current run identifier.root: resolved scope root.
- Verify
input_pathexists and is a readable file. If not: updatepipeline-state.jsonphases[0].status = "blocked"; emitNEEDS_CONTEXTwith message: "Input markdown file not found at{input_path}. Provide a valid path and re-run." - Read the file content. If the file is empty: write a zero-count
frequency-counts.jsonand emitDONE_WITH_CONCERNSwith message: "Input file at{input_path}is empty. Frequency counts file written with zero entries."
2. PROCESS
Step 2.1 — Strip markdown syntax:
Remove the following before tokenizing (do not count these as word content):
- ATX headings (
#,##, etc.) - Emphasis markers (
*,**,_,__) - Inline code and code fences (content inside backticks)
- URLs and link syntax (
[text](url)→ keeptext, discardurl) - HTML tags if present
- Punctuation attached to word boundaries (
,,.,:,;,!,?,",',(,),[,],{,})
Step 2.2 — Tokenize:
Split the cleaned text on whitespace. Convert every token to lowercase. Discard any token that is empty or contains only non-alphabetic characters (e.g., ---, 123, 42px).
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.
- 7d ago First seen · 115 lines · 43 tokens per session scan A 00ba12375a29
tokenizer-protocol is a skill published in the GitHub repository gustavo-meilus/superpipelines (4 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 1,469 once invoked, about $0.0002 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
orchestrated-execution
Execute work units through the rigorous 4-phase Metaswarm cycle (Implement -> Validate -> Adversarial Review -> Commit) with independent quality gate enforcement.
quality-checklist
Validate implementation quality through custom checklists, scoring against constitution standards, specification coverage, and producing remediation recommendations.
verification
Verification-before-completion discipline ensuring all success criteria are met, tests pass, and reviews complete before declaring work done.
check
Confirm a change before merge. /check verify drives the real app to prove behavior against the spec (every acceptance criterion met, every surface built). /check review runs a senior code review on a fresh model, one that did not write the code. Verify after /develop, review before a PR. Writes to docs/reviews/, never…
refactor
Refactors code for quality and maintainability. Triggers: refactor, clean up, restructure, improve code, modernize.
prompt-caching-patterns
Anthropic API prompt caching: TTL, breakpoints, stacking, invalidation, hit rate. Triggers: prompt caching, cachecontrol, cache breakpoint, cache TTL, hit rate.