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-checknpx skills add fizzbee-io/fizzbee --skill fizz-checkgit 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-check)<a href="https://agentmods.dev/skills/fizzbee-io/fizzbee/fizz-check"><img src="https://agentmods.dev/badge/skills/fizzbee-io/fizzbee/fizz-check.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 | $0.00045 | $0.02479 |
| Opus 5 | $0.00023 | $0.01239 |
| Sonnet 5 | $0.00009 | $0.00496 |
| Haiku 4.5 | $0.00005 | $0.00248 |
Grade A, and why
fizz-check 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 4d 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 — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FizzBee Model Checker
Installation
brew tap fizzbee-io/fizzbee && brew install fizzbee
Running
fizz spec.fizz # full model checking (exhaustive)
fizz -x --max_runs 1 --seed 42 spec.fizz # simulation (single random path)
Note: fizz is the installed binary. If building from source, use ./fizz (wrapper script in the repo root).
All Flags
| Flag | Default | Description |
|---|---|---|
-x / --simulation |
off | Simulation mode: single random path, fast |
--seed N |
0 | Random seed for reproducible simulation / random exploration |
--max_runs N |
0 (unlimited) | Number of simulation runs (simulation mode only) |
--exploration_strategy |
bfs |
State exploration: bfs, dfs, or random (model checking) |
--trace "line1\nline2" |
— | Guided trace: follow specific action sequence |
--trace-file FILE |
— | Load guided trace from file |
--trace-extend N |
0 | After trace, explore N more steps (shows enabled actions) |
--preinit-hook "STMT" |
— | Override constants before Init runs |
--preinit-hook-file FILE |
— | Load preinit hook from .cfg file |
--output-dir DIR |
auto-timestamped | Where to write output |
--no-copy-ast |
off | Don't copy AST to output dir |
--experimental_processed_queue |
off | EXPERIMENTAL: queue holds processed yield-points instead of unprocessed action-starts. Dedupes successors before they enter the queue → smaller peak queue memory (~10× on BFS, ~3× on DFS). State space and assertion outcomes unchanged under BFS. Under DFS / Random with max_actions set, exploration order differs and may visit a different subset within the bound — see Gotchas. |
Understanding Output
Model checking specs/counter.json
StateSpaceOptions: options:{max_actions:100 max_concurrent_actions:2}
Nodes: 12, queued: 0, elapsed: 2.1ms
Valid Nodes: 12 Unique states: 8
IsLive: true
PASSED: Model checker completed successfully
- Nodes: total graph nodes explored
- Valid Nodes: nodes that passed all safety assertions
- Unique states: distinct system states (after symmetry reduction)
- IsLive: liveness assertions passed
- PASSED / FAILED: overall result
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.
- 4d ago First seen · 247 lines · 45 tokens per session scan A 1233fafbdfa3
fizz-check is a skill published in the GitHub repository fizzbee-io/fizzbee (347 stars, last pushed 9d ago), licensed Apache-2.0. It adds 45 tokens to every session and 2,479 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 2026-08-30.
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…
vera-language
Write programs in the Vera programming language. Use when asked to write, edit, debug, or review Vera code (.vera files). Vera is a statically typed, purely functional language with algebraic effects, mandatory contracts, and typed slot references (@T.n) instead of variable names.
propagate
Generate tests from Allium specifications. Use when the user wants to propagate tests, generate test files from a spec, write tests for a specification, create property-based tests, produce state machine tests, check test coverage against spec obligations, or understand what tests a specification requires.
allium
Give your AI agents something more useful than a prompt. Velocity through clarity.
elicit
Run a structured discovery session to build an Allium specification through conversation. Use when the user wants to create a new spec from scratch, elicit or gather requirements, capture domain behaviour, specify a feature or system, define what a system should do, or is describing functionality and needs help…