A dependency-impact tool that lists what a function, route, class, or code change reaches and what reaches it. It can include links between files, languages, and service boundaries.

Use it to estimate the blast radius of a change, find who uses a piece of code, and review which parts may break.

It helps reveal callers and dependent code that a simple text search may miss before you rename, remove, refactor, or change an interface.

glia-impact — Skill for Claude Code by James-Chahwan/repo-graph

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.

Any agent

npx skills add James-Chahwan/repo-graph --skill glia-impact

Clone the repo

git clone --depth 1 https://github.com/James-Chahwan/repo-graph

Made for: Claude Code.

Or install repo-graph, the plugin that ships this one along with the rest of its 8 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/james-chahwan/repo-graph/glia-impact/github.svg)](https://agentmods.dev/skills/james-chahwan/repo-graph/glia-impact)

Your own site

<a href="https://agentmods.dev/skills/james-chahwan/repo-graph/glia-impact"><img src="https://agentmods.dev/badge/skills/james-chahwan/repo-graph/glia-impact/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/james-chahwan/repo-graph/glia-impact"><img src="https://agentmods.dev/badge/skills/james-chahwan/repo-graph/glia-impact.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 960 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.

Model	Per session	Once invoked
Fable 5.1	$0.00072	$0.00960
Opus 5.5	$0.00029	$0.00384
Sonnet 5.5	$0.00014	$0.00192
Haiku 4.5	$0.00007	$0.00096

Measured 5d ago against content hash dfff65d61b0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

glia-impact 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 5d 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-plugin/skills/glia-impact/SKILL.md · 33 lines

How it starts

The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Impact before a change

Know what a change touches before you make it, including the callers grep can't link: other files, other languages, the other side of an HTTP or queue boundary.

Transports

Use whichever is available, in this order: the repo-graph MCP tools when loaded (mcp__repo-graph__<tool>, or mcp__plugin_repo-graph_repo-graph__<tool> from the Claude Code plugin; they may be deferred, so search your tool list first); the glia CLI when on PATH; else uvx --from glia-cli glia <command> .. (no install; the first run downloads the wheel); else uvx mcp-repo-graph <verb>. The MCP tools and uvx mcp-repo-graph print the same text; the glia CLI answers the same question with --json rows (file, line, tier). Run any of them at the repo root (. below).

Want	MCP tool call	glia CLI	uvx mcp-repo-graph
Both directions, 4 hops	`impact nodes=<node>`	`glia blast-radius . <node> --json`	`uvx mcp-repo-graph impact "<node>"`
Who calls or depends on it (upstream)	`impact nodes=<node> direction=backward`	`glia blast-radius . <node> --direction backward --json`	`uvx mcp-repo-graph impact "<node>" --direction backward`
Direct neighbours only	`impact nodes=<node> depth=1`	`glia blast-radius . <node> --depth 1 --json`	`uvx mcp-repo-graph impact "<node>" --depth 1`
The uncommitted change	`impact nodes=<a>,<b>,<c>`	`glia diff-impact . --json`	`uvx mcp-repo-graph impact "<a>,<b>,<c>"`
A PR, as one report		`glia review . --base main --title "<PR title>" --json`
Who implements X, who serves a route		`glia implementors . <node> --json`, `glia serves . "GET /api/orders" --json`

Steps

Run it before you edit. Seed it with a name or qname; don't know it yet? Get it from the graph, not grep: glia find . <word> --json. Several seeds are one walk and one ranking.
Read the rows. They're ranked by relevance to the seeds (the files list ranks the files, co-change first when glia history sync . has run), and each has file, line, a reason saying why it's in scope (CALLS, HTTP_CALLS, HANDLED_BY ...) and its depth. live: false (⊘) means no entry point reaches the node, so it's likely dead; --live-only drops those.
For a change, skip the seeds: glia diff-impact . --json reads the uncommitted diff (--base main for a branch). For a PR, glia review . --base main --title "<PR title>" --json adds the tests to run, the edges by tier, new rule violations and the files the title's ids route to.
Report what's affected by tier (entry, service, handler, data). Call out what grep would miss: transitive dependents, callers in another file or service, and anything marked ⊘.

Read the full file on GitHub · 33 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.

5d ago First seen · 33 lines · 72 tokens per session scan A dfff65d61b0f

Subscribe to this mod's changes

glia-impact is a skill published in the GitHub repository James-Chahwan/repo-graph (55 stars, last pushed 3d ago), licensed MIT. It adds 72 tokens to every session and 960 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-11-02.

Code review

glia-impact next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
glia-impactJames-Chahwan/repo-graph	Skill	55	3d ago	MIT	A	72	Claude Code
autoreviewopenclaw/clawhub	Skill	9.5k	yesterday	MIT	A	17	Claude Code, Codex
agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skills	Skill	2.2k	6d ago	MIT	A	115	Claude Code, Codex
omh-code-reviewrlaope/oh-my-hermes	Skill	5.2k	yesterday	MIT	A	48	Claude Code, Codex
revdiff-planumputun/revdiff	Skill	945	yesterday	MIT	A	84	Claude Code
explore-unknownsdzhng/skills	Skill	1.4k	2d ago	MIT	A	162	Claude Code, Codex
re0-mergeLilMGenius/paperthin	Skill	1.4k	4d ago	MIT	A	70	Claude Code