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 younes-io/agent-skills --skill tla-checkgit clone --depth 1 https://github.com/younes-io/agent-skillsWrote 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/younes-io/agent-skills/tla-check)<a href="https://agentmods.dev/skills/younes-io/agent-skills/tla-check"><img src="https://agentmods.dev/badge/skills/younes-io/agent-skills/tla-check/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/younes-io/agent-skills/tla-check"><img src="https://agentmods.dev/badge/skills/younes-io/agent-skills/tla-check.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 | $0.00079 | $0.01392 |
| Opus 5 | $0.00039 | $0.00696 |
| Sonnet 5 | $0.00016 | $0.00278 |
| Haiku 4.5 | $0.00008 | $0.00139 |
Grade A, and why
tla-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 11d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TLA+ Check
Outputs
- TLA+ spec(s):
*.tla - TLC config(s):
*.cfg - TLC run artifacts:
.tla-check/runs/<run-id>/...(logs and a JSON trace when TLC reports a counterexample)
Non-Negotiables (Honesty Rules)
- Never say "proved correct". Say "no counterexample found" and state the bounds/model used.
- Always surface modeling assumptions you introduced to remove ambiguity.
- If liveness is in scope, explicitly state fairness assumptions used in the run (
WF_/SF_), or explicitly say "none (safety-only run)". - Actively guard against vacuous success before calling a run "pass":
- Show that at least one non-stuttering transition is reachable.
- If using
CONSTRAINT/ACTION_CONSTRAINT, list each one and the behavior it excludes. - Reject properties that are tautological or trivially weakened.
- If any vacuity check is inconclusive, report "inconclusive coverage" instead of "pass".
Workflow (NL -> Spec+CFG -> TLC -> Iterate)
1) Pin Down Scope and Bounds (Ask, Don't Guess)
Ask for (and record) answers:
- What are the state variables?
- What are the actions/steps?
- What safety properties must never break? (invariants)
- What liveness properties must eventually happen? (temporal properties)
- If liveness is in scope, what fairness model applies to which actions? (
WF_/SF_) - What environment/failure model is in-scope? (message loss, crashes, reordering, clock skew, retries)
- What bounds make the model finite? (small sets for nodes, messages, values, time, etc.)
If the user doesn't specify bounds, propose minimal ones (and label them as "proposed"):
- 2-3 nodes, 2-3 values, short message buffers, small time domain.
2) Write the Minimal Spec Skeleton (Then Grow It)
Use a consistent structure:
CONSTANTSfor bounded sets (e.g.,Nodes,Values).VARIABLESfor state.Vars == <<...>>as a single canonical variable tuple name. Use the same casing (Vars) everywhere.TypeOK(type invariant) to keep the model honest.InitandNext(withUNCHANGEDfor untouched vars).- For safety checks:
Spec == Init /\\ [][Next]_Vars. - For liveness checks: extend
Specwith explicit fairness assumptions, e.g./\\ WF_Vars(SomeAction)or/\\ SF_Vars(SomeAction). - Named invariants as separate operators so they can be listed in the
.cfg.
What ships with it
4 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.
- 11d ago First seen · 134 lines · 79 tokens per session scan A d3bfcbf708d7
tla-check is a skill published in the GitHub repository younes-io/agent-skills (20 stars, last pushed 2mo ago), licensed MIT. It adds 79 tokens to every session and 1,392 once invoked, about $0.0004 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
epistemic-uncertainty-quantification
Extend Sounio's epistemic types with advanced uncertainty quantification methods, such as confidence intervals, non‑Gaussian distributions, and Dempster‑Shafer evidence combination, positioning the language at the state‑of‑the‑art in measurement science.
automatic-differentiation-advanced
Extend Sounio's automatic differentiation capabilities to higher‑order derivatives, Hessians, differentiation through control flow, and GPU‑accelerated gradient computation, enabling state‑of‑the‑art scientific machine learning.
formal-verification-epistemic
Integrate formal verification tools (SMT solvers, Lean) to prove properties of epistemic programs, such as uncertainty bounds, confidence guarantees, and provenance integrity, establishing Sounio as a language with mathematically verified scientific claims.
lean-axiom-provenance
Find out what a Lean 4 project actually rests on, and why. Reports every theorem reaching a sorry anywhere upstream, everything settled by nativedecide rather than the kernel, and the shortest path from any declaration to any axiom with each hop labelled a statement dependency or a proof dependency. Use when the user…
lean-generated-proof-audit
Check whether a machine-generated Lean 4 proof actually proves its theorem. A proof can appear in the environment, pass lake build, and still not have been proved: when elaboration fails Lean admits the declaration carrying sorryAx, which an axiom report cannot tell apart from a sorry somebody typed. Use when auditing…
sounio-epistemic-types
Work on Sounio epistemic computing: Knowledge/uncertainty/confidence/provenance, ontology bindings, and dependent epistemic subtyping/proofs; use when editing compiler/src/epistemic/, compiler/src/dependent/, or stdlib/epistemic/.