tlaplus-guided-code-repair

tlaplus-guided-code-repair is a skill for Claude Code, Codex from ArabelaTso/Skills-4-SE. It costs 142 tokens per session (1,414 once invoked), scanned A, original, Apache-2.0.

A repair assistant that uses TLA+ model-checking results to identify and modify C or C++ code. TLA+ is a language for describing and checking system behavior, while a counterexample trace shows how a rule was broken.

In plain words
What is it for?
Analyze invariant violations, deadlocks, or temporal-property failures from TLC traces and generate minimal C/C++ repairs.
Why use it?
It connects an abstract model-checking failure to the implementation, reducing the manual work needed to find and correct the corresponding code defect.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Analyze invariant violations, deadlocks, or temporal-property failures from TLC traces and generate minimal C/C++ repairs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/arabelatso/skills-4-se/tlaplus-guided-code-repair
Install

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.

Any agent
npx skills add ArabelaTso/Skills-4-SE --skill tlaplus-guided-code-repair
Clone the repo
git clone --depth 1 https://github.com/ArabelaTso/Skills-4-SE

Made for: Claude Code, Codex.

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.

agentmods badge for tlaplus-guided-code-repair

README.md
[![agentmods](https://agentmods.dev/badge/skills/arabelatso/skills-4-se/tlaplus-guided-code-repair/github.svg)](https://agentmods.dev/skills/arabelatso/skills-4-se/tlaplus-guided-code-repair)
Your own site
<a href="https://agentmods.dev/skills/arabelatso/skills-4-se/tlaplus-guided-code-repair"><img src="https://agentmods.dev/badge/skills/arabelatso/skills-4-se/tlaplus-guided-code-repair/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.

agentmods 80×15 button for tlaplus-guided-code-repair

Your own site · 80×15
<a href="https://agentmods.dev/skills/arabelatso/skills-4-se/tlaplus-guided-code-repair"><img src="https://agentmods.dev/badge/skills/arabelatso/skills-4-se/tlaplus-guided-code-repair.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 142 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,414 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00142 $0.01414
Opus 5 $0.00071 $0.00707
Sonnet 5 $0.00028 $0.00283
Haiku 4.5 $0.00014 $0.00141

Measured 9d ago against content hash eed33985cd09, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

tlaplus-guided-code-repair 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 9d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/parse_tlc_trace.py, scripts/run_tlc.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/tlaplus-guided-code-repair/SKILL.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TLA+ Guided Code Repair

Automatically repair C/C++ code based on TLA+ model checking violations. This skill analyzes TLC counterexamples, identifies root causes in the implementation, and generates semantically justified repairs.

Repair Workflow

Follow this sequential process when given a TLA+ violation:

1. Parse the Counterexample

Use scripts/parse_tlc_trace.py to extract structured information from TLC output:

python scripts/parse_tlc_trace.py trace.txt
# Or for JSON output:
python scripts/parse_tlc_trace.py --json trace.txt

This extracts:

  • Violation type (invariant, deadlock, temporal)
  • Violated property name
  • State trace with variable values at each step

2. Analyze the Violation

Read the reference guides to understand the violation:

  • references/repair_patterns.md - Common violations and repair strategies
  • references/tlaplus_to_cpp_mapping.md - How to map TLA+ to C/C++ code

Key analysis steps:

  1. Identify which invariant/property was violated
  2. Examine the state trace to find where the violation occurred
  3. Determine which TLA+ action led to the violation
  4. Map the TLA+ action to the corresponding C/C++ function

Example analysis:

Violation: Invariant BalanceNonNegative violated
Final state: balance = -50
Action: Withdraw (line 45 in spec)
Cause: withdraw() function allows amount > balance

3. Identify the Root Cause

Trace backwards from the violation to find the program-level bug:

Common root causes:

  • Missing precondition checks (guards)
  • Race conditions (missing synchronization)
  • Incorrect lock ordering (deadlocks)
  • Uninitialized variables
  • Missing notifications (liveness violations)

Mapping strategy:

  • TLA+ guards → C++ precondition checks
  • TLA+ atomic actions → C++ critical sections
  • TLA+ state variables → C++ member variables/globals
  • TLA+ action sequences → C++ function call chains

4. Generate the Repair

Create a minimal, semantically justified code modification:

Read the full file on GitHub · 183 lines

Files

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.

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.

  1. 9d ago First seen · 183 lines · 142 tokens per session scan A eed33985cd09

Subscribe to this mod's changes

tlaplus-guided-code-repair is a skill published in the GitHub repository ArabelaTso/Skills-4-SE (252 stars, last pushed 22d ago), licensed Apache-2.0. It adds 142 tokens to every session and 1,414 once invoked, about $0.0007 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 2026-09-03.

Related

Other skills, from other repositories

perf-profiler

A performance investigation guide that uses repeatable measurements and profiling evidence to find where software spends time or resources. Profiling records runtime activity such as CPU use, memory use, database work, or network delays.

laolaoshiren/claude-code-skills-zh · 78 tokens

log-analyzer

A log-analysis helper that reads application and system logs to find unusual patterns and likely causes. Logs are records of events such as errors, requests, warnings, and service activity.

laolaoshiren/claude-code-skills-zh · 24 tokens

trace

Trace Elixir call trees from entry points via mix xref. Use when debugging data flow, planning signature changes, or understanding how a bug reaches code.

oliver-kriska/claude-elixir-phoenix · 33 tokens

code-review-web

Review web application code for bugs, security issues, performance problems, and stack-specific anti-patterns. Use this skill whenever the user wants to review code, debug a production issue, investigate a build failure, audit security, or check a PR before merging. Triggers on code review, review my code, debug…

rampstackco/claude-skills · 121 tokens

bim-consistency-checker

Check BIM model consistency: naming conventions, parameter completeness, spatial relationships, and data integrity across model elements.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction · 28 tokens

022-root-cause-analysis

Use when a framed problem needs root-cause investigation rather than a symptom-level fix, applying Five Whys, Fishbone (Ishikawa), Current Reality Tree, and constraint identification. This should trigger when an issue's Root Cause Analysis point of view needs evaluation, or when a maintainer directly asks to find the…

jabrena/plinth · 85 tokens