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/fizzbee-io/fizzbee/fizz-specnpx skills add fizzbee-io/fizzbee --skill fizz-specgit clone --depth 1 https://github.com/fizzbee-io/fizzbeeWrote 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/fizzbee-io/fizzbee/fizz-spec)<a href="https://agentmods.dev/skills/fizzbee-io/fizzbee/fizz-spec"><img src="https://agentmods.dev/badge/skills/fizzbee-io/fizzbee/fizz-spec.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 | $0.00053 | $0.03472 |
| Opus 5 | $0.00026 | $0.01736 |
| Sonnet 5 | $0.00011 | $0.00694 |
| Haiku 4.5 | $0.00005 | $0.00347 |
Grade A, and why
fizz-spec 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 3d 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 — 450 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FizzBee Spec Writing
FizzBee is a Python-like formal spec language built on Starlark. Specs model distributed systems; the model checker exhaustively verifies safety and liveness properties.
Full reference: ~/.claude/skills/fizzbee-docs/LANGUAGE_REFERENCE.md
Examples index: ~/.claude/skills/fizzbee-docs/README.md
Installation
brew tap fizzbee-io/fizzbee && brew install fizzbee
# Then run: fizz spec.fizz
File Structure
---
# Optional YAML frontmatter
options:
max_actions: 100
max_concurrent_actions: 2 # 1 for single-user apps
crash_on_yield: true # enable fault injection
action_options:
"RoleName.ActionName":
max_actions: 10
deadlock_detection: true # false for interactive apps
liveness: strict
---
Then the Fizz spec:
- Top-level constants
- Functions (pure helpers)
- Roles (actors/processes)
- Top-level actions (Init + others)
- Assertions
Core Syntax
Constants and Global State
MAX = 10 # constant
State = enum('IDLE', 'RUNNING') # enum
action Init:
counter = 0 # becomes global state variable
items = []
server = Server() # create role instance
Actions
# Modifier order: [flow] [fairness] action Name
atomic action Increment: # atomic = no interleaving
counter = counter + 1
fair action Progress: # fair = weak fairness
require not done
done = True
atomic fair action Produce: # both modifiers
require len(queue) < MAX
queue.append(item)
Key rules:
- No parameters on actions
Initruns once; all variables defined in it become global staterequire conditiondisables the action (doesn't execute it)- An action is "enabled" only after it executes a simple statement (
=, method call,pass)
Roles
@state(ephemeral=['cache']) # cache resets on crash
role Server:
action Init:
self.data = {} # role state (persists)
self.cache = {} # ephemeral (resets on crash)
atomic func Read(key): # function: can have params + return
return self.data.get(key, None)
action Write:
key = oneof self.pending_keys
self.data[key] = self.pending[key]
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.
- 3d ago First seen · 450 lines · 53 tokens per session scan A 1038ef38ce04
fizz-spec is a skill published in the GitHub repository fizzbee-io/fizzbee (347 stars, last pushed 8d ago), licensed Apache-2.0. It adds 53 tokens to every session and 3,472 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
tla-check
Write and iteratively refine executable TLA+ specs (.tla) and TLC model configs (.cfg) from natural-language system designs; run TLC model checking; summarize pass/fail and counterexamples with explicit assumptions and bounds. Use when asked to design or validate a protocol/state machine, create or edit .tla/.cfg…
tla-proof
Write and iteratively refine TLA+ theorem proofs in .tla modules with TLAPS (tlapm); run proof checks and summarize proved vs failed/omitted obligations with explicit assumptions and trust boundaries. Use when asked to create or fix THEOREM or PROOF blocks, diagnose TLAPS failures, strengthen inductive invariants…
learn-from-math-agent-trajectories
Review completed or paused mathematical agent transcripts, visible reasoning, code, searches, tool calls, corrections, and final claims to extract evidence-backed lessons for Jacobian operations, discovery, contracts, skills, evaluations, and documentation. Use for mathematical workflow retrospectives and "what should…
decompose-mathematical-solution-corpora
Decompose a bounded corpus of mathematical proofs, formalizations, scripts, and certificates into recurring solution techniques and the smallest reusable Jacobian postconditions. Use for repository- or corpus-level “what can Jacobian learn?” audits; do not use for one operation contract or one agent trajectory.
verifier-evaluations
Design, audit, and repair fail-closed mathematical verifiers and evaluation contracts, including public schemas, frozen-input binding, task-specific witnesses, diagnostic scoring, adversarial fixtures, and Oracle validation. Use when a verifier can crash, accept malformed claims, reject equivalent witnesses, leak…
audit-mathematical-vocabulary
Audit one bounded Jacobian mathematical slice for missing or unusable executable vocabulary using source demand, catalog composition, contract evidence, and maintained-backend feasibility. Use for proactive gap audits that are broader than one operation but narrower than a repository-wide inventory; do not use for…