A TLA+ model-checking skill for verifying a thread-dispatch design. TLA+ describes concurrent systems, and its checker explores possible states to find deadlocks, broken rules, or tasks that never finish.

Use it after changing thread dispatch, file ownership, joining, cancellation, budgets, or related data models. It checks the configured invariants and liveness properties and reports whether the model passes.

It exposes concurrency problems that may only appear under unusual timing or ordering. Counterexample traces show the sequence of states that caused a failure.

How joelreymont/pz configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to joelreymont/pz. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/joelreymont/pz/main/.claude/skills/tla/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/joelreymont/pz

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/joelreymont/pz/tla/github.svg)](https://agentmods.dev/skills/joelreymont/pz/tla)

Your own site

<a href="https://agentmods.dev/skills/joelreymont/pz/tla"><img src="https://agentmods.dev/badge/skills/joelreymont/pz/tla/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/joelreymont/pz/tla"><img src="https://agentmods.dev/badge/skills/joelreymont/pz/tla.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 562 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00041	$0.00562
Opus 5	$0.00020	$0.00281
Sonnet 5	$0.00008	$0.00112
Haiku 4.5	$0.00004	$0.00056

Measured 10d ago against content hash b78838917081, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

tla 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 10d 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.

.claude/skills/tla/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TLA+ Model Check

Run TLC on docs/tla/ThreadDispatch.tla to verify thread dispatch invariants.

When to Run

After modifying thread dispatch, file ownership, join/cancel, or budget logic in EPISODES-PLAN.md
After changing Thread/Episode data model
After modifying any resolved decision that affects concurrency

Command

/opt/homebrew/opt/openjdk/bin/java -XX:+UseParallelGC \
  -cp ~/tools/tla2tools.jar tlc2.TLC \
  docs/tla/ThreadDispatch.tla \
  -config docs/tla/ThreadDispatch.cfg \
  -workers auto

Run from project root. Expected: ~3-4M states, <3 minutes, exit code 0.

Interpreting Results

No errors, exit 0: all invariants and temporal properties hold.
Deadlock reached: a state has no successor. Check if it's a valid terminal state (orch_state="done", round=MaxRounds) or a real bug.
Invariant violated: TLC prints the violating state trace. Read the trace to find which property broke and in which state transition.
Temporal property violated: liveness failure — a thread never completes, join never terminates, or cancel never propagates. The counterexample trace shows the lasso (cycle).

Updating the Spec

When the episodes plan changes:

Update ThreadDispatch.tla to match new design decisions
Run TLC to verify
If state space explodes (>10M states or >5 min), reduce constants in .cfg (fewer threads/files/rounds) — the properties are symmetry-invariant

Verified Properties

Safety (invariants):

FileOwnershipDisjoint: no two concurrent threads share files
BudgetNonNegative: no thread overspends
GlobalBudgetNonNegative: total budget never negative
ToolMaskValid: no privilege escalation
DepthOneEnforced: no sub-thread spawning
FileLocksConsistent: locks match ownership
EpisodesFromCompleted: episodes only from done/failed threads
JoinCompleteness: orchestrator done only after all episodes collected

Liveness (temporal):

ThreadProgress: running threads eventually complete
JoinTermination: join always terminates
CancelResponsiveness: aborted threads eventually fail

Read the full file on GitHub · 59 lines

Changes

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.

10d ago First seen · 59 lines · 41 tokens per session scan A b78838917081

Subscribe to this mod's changes

tla is a skill published in the GitHub repository joelreymont/pz (95 stars, last pushed 5mo ago), licensed MIT. It adds 41 tokens to every session and 562 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.

Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

pz: Skill for Claude Code