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 esbmc/agent-marketplace --skill esbmc-verificationgit clone --depth 1 https://github.com/esbmc/agent-marketplaceWrote 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/esbmc/agent-marketplace/esbmc-verification)<a href="https://agentmods.dev/skills/esbmc/agent-marketplace/esbmc-verification"><img src="https://agentmods.dev/badge/skills/esbmc/agent-marketplace/esbmc-verification/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/esbmc/agent-marketplace/esbmc-verification"><img src="https://agentmods.dev/badge/skills/esbmc/agent-marketplace/esbmc-verification.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 | $0.00242 | $0.02994 |
| Opus 5 | $0.00121 | $0.01497 |
| Sonnet 5 | $0.00048 | $0.00599 |
| Haiku 4.5 | $0.00024 | $0.00299 |
Grade A, and why
esbmc-verification scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ESBMC Verification Skill
ESBMC (Efficient SMT-based Context-Bounded Model Checker) detects bugs or proves their absence in C, C++, CUDA, CHERI-C, Python, Solidity, Java, and Kotlin programs.
Prerequisites Check
Before running any ESBMC command, verify that ESBMC is installed by running which esbmc or esbmc --version. If ESBMC is not found, inform the user and provide installation instructions:
- Pre-built binaries: Download from ESBMC releases
- Build from source: Clone https://github.com/esbmc/esbmc and follow the build instructions in its README
- After installing, ensure
esbmcis in the PATH:export PATH=$PATH:/path/to/esbmc/bin
Do not proceed with verification commands until ESBMC is confirmed available.
Verification Pipeline
Source Code → Frontend Parser → GOTO Program → Symbolic Execution (SSA) → SMT Formula → Solver → Result
Quick Start
# C file with default checks
esbmc file.c
# C++ file
esbmc file.cpp
# Python (requires type annotations)
esbmc file.py
# Solidity contract
esbmc --sol contract.sol --contract ContractName
# Common safety checks
esbmc file.c --memory-leak-check --overflow-check --unwind 10 --timeout 60s
# Concurrency verification
esbmc file.c --deadlock-check --data-races-check --context-bound 2
Supported Languages
| Language | Command | Notes |
|---|---|---|
| C | esbmc file.c |
Default, Clang frontend |
| C++ | esbmc file.cpp |
C++11-20 via --std |
| Python | esbmc file.py |
Requires type annotations, Python 3.10+ |
| Solidity | esbmc --sol file.sol --contract Name |
Smart contracts |
| CUDA | esbmc file.cu |
GPU kernel verification |
| Java/Kotlin | esbmc file.jimple |
Requires Soot conversion from .class |
For language-specific options and examples, see references/language-specific.md.
Safety Properties
Default Checks (Always On)
- Array bounds: Out-of-bounds array access
- Division by zero: Integer and floating-point
- Pointer safety: Null dereference, invalid pointer arithmetic
- Assertions: User-defined
assert()statements
What ships with it
15 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.
- examples/concurrent.c 9.9 KB
- examples/cpp-verify.cpp 8.0 KB
- examples/memory-check.c 4.8 KB
- examples/overflow-check.c 7.2 KB
- examples/python-verify.py 18 KB runs code
- references/adding-intrinsics.md 6.6 KB
- references/cli-options.md 12 KB
- references/fixing-failures.md 2.9 KB
- references/function-contracts.md 15 KB
- references/intrinsics.md 9.3 KB
- references/language-specific.md 11 KB
- references/loop-invariants.md 11 KB
- references/verification-strategies.md 8.9 KB
- scripts/full-audit.sh 8.0 KB runs code
- scripts/quick-verify.sh 5.6 KB runs code
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 · 278 lines · 242 tokens per session scan A 0ed0ec036597
esbmc-verification is a skill published in the GitHub repository esbmc/agent-marketplace (4 stars, last pushed 6mo ago), licensed MIT. It adds 242 tokens to every session and 2,994 once invoked, about $0.0012 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
experimental-code-coverage-local-debugger
Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
work
Deliver one maintainer-approved EmDash issue, choosing the bug-fix path for a defect and the direct implementation path for an enhancement or task.