atlas.flow

A flow-analysis command traces how code runs from a chosen starting point and describes the business logic along that path. It can switch to focused analyses for topics such as dead code, concurrency, injection risks, state changes, transactions, or logging.

In plain words
What is it for?
Use it to follow requests or functions through a codebase, investigate unreachable code or race conditions, trace untrusted data, map state or transaction changes, and discover behavior from logs.
Why use it?
It helps explain what a piece of code actually does and where important conditions, side effects, or risks appear across the execution path.

Command for Claude Code

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 commands/lis186/sourceatlas/atlas.flow
Clone the repo
git clone --depth 1 https://github.com/lis186/SourceAtlas

Made for: Claude Code.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,864 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 $0.00013 $0.01864
Opus 5 $0.00006 $0.00932
Sonnet 5 $0.00003 $0.00373
Haiku 4.5 $0.00001 $0.00186

Measured 3d ago against content hash ca4cec645290, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

atlas.flow 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 3d 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.

.claude/commands/atlas.flow.md · 240 lines

How it starts

The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SourceAtlas: Flow Analysis

Target: $ARGUMENTS


STEP 0: Mode Detection (EXECUTE IMMEDIATELY)

IMPORTANT: Check these patterns FIRST before doing anything else.

Check for Tier 2-3 Keywords (External Mode Required)

Scan $ARGUMENTS for these keywords. If ANY match, load external file and STOP reading this document:

If arguments contain... Then execute this action
"dead code" OR "unreachable" OR "unused" Read scripts/atlas/flow-modes/mode-13-dead-code.md then follow its instructions
"async" OR "thread" OR "concurrent" OR "race" Read scripts/atlas/flow-modes/mode-14-concurrency.md then follow its instructions
"taint" OR "injection" OR "untrusted" Read scripts/atlas/flow-modes/mode-12-taint-analysis.md then follow its instructions
"state" OR "status" OR "lifecycle" Read scripts/atlas/flow-modes/mode-04-state-machine.md then follow its instructions
"transaction" OR "rollback" OR "commit" Read scripts/atlas/flow-modes/mode-09-transaction.md then follow its instructions
"log" OR "logging" OR "from logs" Read scripts/atlas/flow-modes/mode-06-log-discovery.md then follow its instructions
"compare" OR "diff" OR "vs" Read scripts/atlas/flow-modes/mode-05-flow-comparison.md then follow its instructions
"feature toggle" OR "feature flag" Read scripts/atlas/flow-modes/mode-07-feature-toggle.md then follow its instructions
"cache" OR "redis" OR "TTL" Read scripts/atlas/flow-modes/mode-11-cache-flow.md then follow its instructions

If a keyword matched above: Load the file NOW, then execute ONLY that mode's instructions. Do NOT continue reading this document.

Check for Tier 1 Keywords (Built-in Modes)

If none of the above matched, check for these Tier 1 patterns:

If arguments contain... Mode to use
"who calls" OR "callers" OR "called by" Mode 1: Reverse Tracing (see below)
"error" OR "failure" OR "exception" OR "fail" Mode 2: Error Path (see below)
"data flow" OR "how is X calculated" OR "trace variable" Mode 3: Data Flow (see below)
"event" OR "message" OR "pub/sub" OR "listener" Mode 8: Event Tracing (see below)
"permission" OR "role" OR "auth" OR "access control" Mode 10: Permission Flow (see below)
(none of the above) Standard Flow Tracing (default)

Read the full file on GitHub · 240 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. 3d ago First seen · 240 lines · 0 tokens per session scan A ca4cec645290

Subscribe to this mod's changes

atlas.flow is a command published in the GitHub repository lis186/SourceAtlas (47 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 1,864 once invoked, about $0.0001 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.