source-analysis-agent

A source-code review agent for checking documentation in Solidity projects, which are applications built on a blockchain. It uses targeted searches and file reads instead of loading every source file at once.

In plain words
What is it for?
It counts documented and undocumented functions, contracts, events, and public variables, then reports up to 10 documentation gaps.
Why use it?
It helps find missing or incomplete NatSpec comments, the documentation format used in Solidity code, without manually checking every function and contract.

Agent

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 agents/cdsecurity/cdsecurity-skills/source-analysis-agent
Clone the repo
git clone --depth 1 https://github.com/CDSecurity/cdsecurity-skills
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,284 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 $0.00000 $0.02284
Opus 5 $0.00000 $0.01142
Sonnet 5 $0.00000 $0.00457
Haiku 4.5 $0.00000 $0.00228

Measured 2d ago against content hash 85134fe83709, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

source-analysis-agent 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 2d 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.

audit-prep/references/agents/source-analysis-agent.md · 225 lines

How it starts

The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Source Analysis Agent — Phases 3, 4 & 6

You have: project_dir, in-scope file list, and Grep + Read tools.

CRITICAL: Do NOT read all source files at once. Use targeted Grep queries for each check.

Phase 3: NatSpec Documentation (10%)

Step 1: Count documentable elements

Run these Greps on in-scope files (use the file list from your bundle):

a) Public/external functions: Pattern: function\s+\w+[^;]*(public|external) Count total matches.

b) Contracts/interfaces/libraries: Pattern: (abstract\s+)?(contract|interface|library)\s+\w+

c) Events: Pattern: event\s+\w+

d) Public state variables: Pattern: \w+\s+public\s+\w+;

Step 2: Count NatSpec coverage

a) @inheritdoc count — these are fully documented: Pattern: @inheritdoc

b) @notice before functions: Pattern: @notice Count total. Compare against documentable elements from Step 1.

c) Contract-level @title: Pattern: @title

Step 3: Spot-check gaps

Grep for functions WITHOUT preceding NatSpec:

  • Pattern: function\s+\w+ with -B5 context
  • Scan results for functions not preceded by /// or /** lines
  • Only report the first 10 undocumented functions (cap findings)

Skip standard overrides: Do NOT flag functions that are simple overrides of well-known standards (ERC20, ERC721, ERC1155, ERC4626, etc.) like ownerOf, balanceOf, transferFrom, approve, getApproved, isApprovedForAll, safeTransferFrom, tokenURI, supportsInterface, totalSupply, decimals, name, symbol. These are self-explanatory from the standard — @inheritdoc or @notice is nice but not required. Only flag custom project-specific functions that lack documentation.

Step 4: Stale @param detection

Grep for @param with -A3 context to get the function signature below. Check that each @param name matches an actual parameter in the function. Flag any @param that references a parameter not in the signature (copy-paste error). Deduction: -5 each (cap -15)

Step 5: Missing @return for named returns

Grep for functions with named return values: returns\s*\(.*\w+\s+\w+ For each, check if a matching @return tag exists above. Deduction: -3 each (cap -15)

Read the full file on GitHub · 225 lines

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. 2d ago First seen · 225 lines · 0 tokens per session scan A 85134fe83709

Subscribe to this mod's changes

source-analysis-agent is an agent published in the GitHub repository CDSecurity/cdsecurity-skills (50 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,284 tokens. 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 agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens