dataflow-tracer

dataflow-tracer is an agent for Claude Code from bx33661/oh-my-vul. It costs 74 tokens per session (381 once invoked), scanned A, original, MIT.

A static code-analysis helper that traces how data moves from an input to a dangerous operation and checks. It reads public source code without running the application.

In plain words
What is it for?
Inspecting two to five relevant source files, documenting source-to-sink-to-guard paths, and assigning confidence to vulnerability candidates. For confirmed findings, it writes a ThreatMap sidecar file.
Why use it?
It replaces vague keyword matches with evidence about whether a suspected vulnerability is actually reachable. It also records exact file and line references for confirmed findings.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions Claude Code.

Good fit Inspecting two to five relevant source files, documenting source-to-sink-to-guard paths, and assigning confidence to vulnerability candidates. For confirmed findings, it writes a ThreatMap sidecar file.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/bx33661/oh-my-vul/dataflow-tracer
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.

Clone the repo
git clone --depth 1 https://github.com/bx33661/oh-my-vul

Made for: Claude Code.

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 dataflow-tracer

README.md
[![agentmods](https://agentmods.dev/badge/agents/bx33661/oh-my-vul/dataflow-tracer.svg)](https://agentmods.dev/agents/bx33661/oh-my-vul/dataflow-tracer)
Your own site
<a href="https://agentmods.dev/agents/bx33661/oh-my-vul/dataflow-tracer"><img src="https://agentmods.dev/badge/agents/bx33661/oh-my-vul/dataflow-tracer.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 381 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.
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 $0.00074 $0.00381
Opus 5 $0.00037 $0.00191
Sonnet 5 $0.00015 $0.00076
Haiku 4.5 $0.00007 $0.00038

Measured 8d ago against content hash cb8808d25948, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

dataflow-tracer 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 8d 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.

agents/dataflow-tracer.md · 37 lines

What it actually says

Agent: dataflow-tracer

Delegated by: omv-find, omv-audit

Inspects 2-5 relevant source files per candidate and builds a source → sink → guard note. Also produces the full ThreatMap.v1 sidecar for confirmed findings.

Inputs

  • Repository URL and version/commit
  • Vulnerability class to focus on
  • Known entry points or suspicious files (optional)

Outputs

Per candidate:

  • Concise source → sink → guard note with exact file:line references
  • Confidence level: high | medium | low

Per confirmed finding (full mode):

  • ThreatMap.v1 sidecar at .omv/threatmaps/<id>-threat.yaml (schema: contracts/threat-map.v1.yaml)

Constraints

  • Read public source only (GitHub raw or local checkout). No network probing of live services.
  • Bash is allowed only for running installed scripts. The resolve_source_path.py helper lives at skills/omv-find/scripts/resolve_source_path.py under the Claude Code skills directory.
  • A keyword hit alone is low confidence — prove reachability.
  • High confidence requires at least one exact file/function path.
  • Never run the code; describe static observations only.
  • If you cannot establish a continuous dataflow, say so explicitly. Do not infer.
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. 8d ago First seen · 37 lines · 74 tokens per session scan A cb8808d25948

Subscribe to this mod's changes

dataflow-tracer is an agent published in the GitHub repository bx33661/oh-my-vul (4 stars, last pushed 19d ago), licensed MIT. It adds 74 tokens to every session and 381 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 2026-08-31.

Related

Other agents, from other repositories

diff-reviewer

Reviews an existing working-tree diff for correctness, scope creep, suppressed errors and shortcut fixes. Reports findings only — never edits. Use as a second opinion before the driver accepts a worker's changes.

aiskillstore/marketplace · 43 tokens

swift-staff-engineer

Senior iOS staff engineer reviewer. Use to critically review Swift implementation plans, architecture decisions, and code changes before considering them done. Assumes problems exist — finds them before they ship.

jeremieb/swift-unit-test-instructions · 43 tokens

agent-reviewer

Senior Technical Lead and Security Auditor specializing in code quality, correctness, and security audits.

guanyang/open-agent-hub · 21 tokens

edge-case-explorer

Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…

testdouble/han · 135 tokens

predictive-analyst

Precognition agent. Analyzes code changes to predict impact, regressions, and conflicts BEFORE they happen. Uses dependency graphs and historical data.

softspark/ai-toolkit · 35 tokens

qa-reviewer

Editorial gate. Final pass on phrasing, framework-citation-version accuracy, cross-finding consistency. Flags (never blocks) findings that need author attention.

transilienceai/communitytools · 35 tokens