frama-c-proofreader

frama-c-proofreader is a skill for Claude Code, Codex from sysprog21/frama-c-mcp. It costs 82 tokens per session (546 once invoked), scanned A, original, MIT.

A verification workflow for C programs with ACSL annotations, which are formal statements describing what code should do. It uses Frama-C tools to check those statements through static analysis and, when available, runtime checks.

In plain words
What is it for?
Use it to check C contracts, investigate analysis alarms, inspect proof goals, test proposed annotations, and explain what a formal proof does or does not establish.
Why use it?
It separates proven properties, reported warnings, and tests on particular executions, so developers do not mistake one kind of evidence for another.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/sysprog21/frama-c-mcp/frama-c-proofreader
Any agent
npx skills add sysprog21/frama-c-mcp --skill frama-c-proofreader
Clone the repo
git clone --depth 1 https://github.com/sysprog21/frama-c-mcp

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 frama-c-proofreader

README.md
[![agentmods](https://agentmods.dev/badge/skills/sysprog21/frama-c-mcp/frama-c-proofreader.svg)](https://agentmods.dev/skills/sysprog21/frama-c-mcp/frama-c-proofreader)
Your own site
<a href="https://agentmods.dev/skills/sysprog21/frama-c-mcp/frama-c-proofreader"><img src="https://agentmods.dev/badge/skills/sysprog21/frama-c-mcp/frama-c-proofreader.svg" alt="Measured on agentmods" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 546 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00082 $0.00546
Opus 5 $0.00041 $0.00273
Sonnet 5 $0.00016 $0.00109
Haiku 4.5 $0.00008 $0.00055

Measured 4d ago against content hash 13eef9289b7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

frama-c-proofreader 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 4d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/verify.sh), 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/frama-c-proofreader/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Frama-C Proofreader

Workflow

Prefer the MCP server when it is available. Start with the install check and the shortest useful call:

self_check {}
reload_project {files, rte: true}
check {function?, timeout?}

If check reports alarms or non-valid goals, inspect the concrete payload before changing code:

get_eva_alarms {function?, status?}
investigate_alarm {property_key, depth}
get_wp_goals {function, status?}
get_wp_goals {function, detail: true}
context {function, want: ["current_annotations", "function_ast"]}

Validate candidate ACSL with dry-run injection first:

inject_all_annotations {function, dry_run: true, annotations: [{kind, acsl, ...}]}
inject_all_annotations {function, annotations: [{kind, acsl, ...}]}
run_wp {functions: [function]}

Use run_e_acsl only as runtime evidence for concrete executions. If it is unavailable or fails to compile instrumentation, report that runtime checking was unavailable.

Read references/mcp-workflow.md for the full MCP call order, references/wp-output.md when interpreting WP goals, and references/e-acsl-output.md before making runtime-check claims.

Reporting

Always separate these outcomes:

  • Environment failure: tool missing, prover not configured, instrumentation failed.
  • Static proof gap: WP did not prove a goal; this is not automatically a bug.
  • Runtime violation: E-ACSL found a violation on an executed path.
  • Proven under assumptions: WP proved the generated goals for the ACSL and RTE configuration that actually ran.

Do not claim proof without tool output. Report exact goal names, proof counts, and whether rte: true or -wp-rte was used.

Boundaries

WP proves obligations generated from the C program and ACSL. It does not prove requirements that were omitted from the specification.

EVA alarms and WP goals are complementary. A clean WP result does not replace checking missing frame conditions or assumed callee contracts.

E-ACSL checks only executed paths and inputs. Passing one run is evidence, not exhaustive proof.

Read the full file on GitHub · 58 lines

Files

What ships with it

8 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. 4d ago First seen · 58 lines · 82 tokens per session scan A 13eef9289b7b

Subscribe to this mod's changes

frama-c-proofreader is a skill published in the GitHub repository sysprog21/frama-c-mcp (17 stars, last pushed 4d ago), licensed MIT. It adds 82 tokens to every session and 546 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.

Related

Other skills, from other repositories

ue-mcp-native-cpp

Use when writing or modifying native C++ UCLASSes in an Unreal project via ue-mcp. Covers createcppclass → writecppfile → livecodingcompile loop, when to use build vs Live Coding, and the addmoduledependency workflow. Pulls in any time the user asks to write a new native class, add a UPROPERTY, or implement a…

db-lyon/ue-mcp · 83 tokens

6502-assembly

Use when writing or debugging 6502 assembly for the Commodore 64 with ca65/ld65 via c64 build or c64 run. Covers the C64 program skeleton, the BASIC SYS stub, calling ROM routines, and 6502 gotchas.

nschneir/Project64 · 58 tokens

opengrok-cpp

Specialized patterns for navigating C++ codebases with OpenGrok MCP.

IcyHot09/opengrok-mcp-server · 20 tokens

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

specflow-use

To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.

griddynamics/rosetta · 27 tokens

opik-diagnose

Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…

comet-ml/opik-mcp · 147 tokens