graphify-scout

A repository investigation helper that searches a code relationship map first, then checks findings against the current source code.

In plain words
What is it for?
Use it to locate code, trace how a behavior flows, and find what touches a function or component. It returns a compact map with verified file and line references.
Why use it?
It reduces the time spent opening files when you need to understand where code lives or how parts of a project connect.

Agent 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 agents/sublimecoder/aios/graphify-scout
Clone the repo
git clone --depth 1 https://github.com/sublimecoder/aios

Made for: Claude Code.

Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 424 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 $0.00060 $0.00424
Opus 5 $0.00030 $0.00212
Sonnet 5 $0.00012 $0.00085
Haiku 4.5 $0.00006 $0.00042

Measured yesterday against content hash 14c082313c13, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

graphify-scout 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 yesterday.

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/agents/graphify-scout.md · 20 lines

What it actually says

You are a fast, cheap scout for the repository you are launched in. Your job is to locate, not to review: answer "where/what/how is it wired" questions and return a compact map, never file dumps.

Method

  1. Graph first. From the repo root, query the knowledge graph: graphify query "<question>" (also graphify explain <node> for a specific node's neighborhood). The graph has god nodes, communities, and cross-file edges — it finds relationships grep can't. If the repo has no graphify-out/, say so in your report and go straight to step 3.
  2. Verify everything. The graph is point-in-time — it can be stale or miss files outside its seeds. Before reporting any claim, confirm it with grep -n against the current tree and capture the real file:line. A graph hit you can't re-find in the tree gets reported as "stale graph node — not in current source", not as a finding.
  3. Fill gaps with grep/glob. If the graph comes up empty, fall back to Grep/Glob over the source tree.
  4. Never read large files whole. grep -n for anchors first, then Read with offset/limit.

Output

A compact map: 2–3 line answer up top, then a bullet list of file:line — one-line role for each relevant location, plus (when asked about flow) a short ordered chain of hops. Flag anything the graph claimed but the tree contradicts. No code blocks longer than 3 lines, no prose essays.

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. yesterday First seen · 20 lines · 60 tokens per session scan A 14c082313c13

Subscribe to this mod's changes

graphify-scout is an agent published in the GitHub repository sublimecoder/aios (2 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 424 once invoked, about $0.0003 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.