Borrowing it
Nothing to install: this file belongs to kyleve/Stuff. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kyleve/Stuff/main/.agents/skills/tla-verify-protocol/SKILL.mdgit clone --depth 1 https://github.com/kyleve/StuffWrote 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/kyleve/stuff/tla-verify-protocol)<a href="https://agentmods.dev/skills/kyleve/stuff/tla-verify-protocol"><img src="https://agentmods.dev/badge/skills/kyleve/stuff/tla-verify-protocol/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/skills/kyleve/stuff/tla-verify-protocol"><img src="https://agentmods.dev/badge/skills/kyleve/stuff/tla-verify-protocol.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 | $0.00105 | $0.01587 |
| Opus 5.5 | $0.00042 | $0.00635 |
| Sonnet 5.5 | $0.00021 | $0.00317 |
| Haiku 4.5 | $0.00011 | $0.00159 |
Grade A, and why
tla-verify-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 2mo 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify a protocol with PlusCal and TLA+
Verify one narrow temporal claim, not an application. Treat TLC output as evidence about the stated model, bounds, and assumptions. Never present it as proof that the implementation is correct.
Read the repository and affected module instructions before modeling. In this
repository, use
Where/Specifications/TrackingReconciliation
as the worked tooling and documentation reference. Do not copy its state
mapping into unrelated protocols.
Establish the verification boundary
- Read the production implementation, tests, and callers. Identify every entry point that can participate in the protocol, not only the method named in the request.
- State one correctness question in plain language. Define its admission or linearization points, success and failure outcomes, repeated-call behavior, and treatment of work racing with shutdown or cancellation.
- Record the source revision and files the model represents. List suspension points, locks, actor reentrancy, tasks, callbacks, persistence boundaries, and environment actions that can change ordering.
- If a missing product decision changes the contract materially, stop and request direction. If the logic has no meaningful temporal behavior, explain why TLA+ is the wrong verification tool.
Read references/modeling-checklist.md
before authoring any model. Read only the relevant sections of
references/protocol-patterns.md for the
protocol family being checked.
Build a traceable model
- Create a source-correspondence table mapping each model variable and action to production state and code boundaries.
- Preserve independently authoritative facts as separate variables. Do not collapse desired, persisted, in-flight, effective, and published state merely because the implementation calls all of them "state."
- Make each action genuinely atomic. Split an async function at every await or callback boundary where another action can interleave.
- Abstract data values into a small finite set while preserving identity, ordering, duplication, loss, and lifecycle facts relevant to the claim.
- Model environment failures and late completions nondeterministically unless the production contract forbids them.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 151 lines · 105 tokens per session scan A fe8493704757
tla-verify-protocol is a skill published in the GitHub repository kyleve/Stuff (4 stars, last pushed today), licensed Apache-2.0. It adds 105 tokens to every session and 1,587 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
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.
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".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.