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 agentmods add skills/lis186/sourceatlas/flownpx skills add lis186/SourceAtlas --skill flowgit clone --depth 1 https://github.com/lis186/SourceAtlasWhat 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 | $0.00015 | $0.01920 |
| Opus 5 | $0.00008 | $0.00960 |
| Sonnet 5 | $0.00003 | $0.00384 |
| Haiku 4.5 | $0.00002 | $0.00192 |
Grade A, and why
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 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.
How it starts
The opening of the file, as written. The whole thing — 250 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) |
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.
- 2d ago First seen · 250 lines · 0 tokens per session scan A 1f572eb5f531
flow is a skill published in the GitHub repository lis186/SourceAtlas (47 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 1,920 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…