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 skills add James-Chahwan/repo-graph --skill gliagit clone --depth 1 https://github.com/James-Chahwan/repo-graphWrote 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.
[](https://agentmods.dev/skills/james-chahwan/repo-graph/glia)<a href="https://agentmods.dev/skills/james-chahwan/repo-graph/glia"><img src="https://agentmods.dev/badge/skills/james-chahwan/repo-graph/glia/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.
<a href="https://agentmods.dev/skills/james-chahwan/repo-graph/glia"><img src="https://agentmods.dev/badge/skills/james-chahwan/repo-graph/glia.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00194 | $0.04311 |
| Opus 5.5 | $0.00078 | $0.01724 |
| Sonnet 5.5 | $0.00039 | $0.00862 |
| Haiku 4.5 | $0.00019 | $0.00431 |
Grade A, and why
glia 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
glia from the command line
glia parses a repo into one cross-language graph and answers questions from it. The graph holds calls, imports, the HTTP / gRPC / GraphQL / queue / event / WebSocket links between services, data access, tests and docs. Each answer is one glia <command> <repo> ... call. Add --json for structured output (progress lines go to stderr). Open the file:line an answer gives and read it there rather than grepping for it.
On a repo you have not seen before, run glia health <repo> --json first. It says, per boundary mechanism (HTTP, gRPC, RPC, GraphQL, queues, WebSocket), how much of the client and server side the graph pairs, with a verdict OK, DEGRADED or BLIND, plus the code files no parser read and the workspace imports left unbound. Where a mechanism is BLIND, an answer that depends on it ("0 breaking", "nothing calls this route") means glia could not see, not that nothing is there: grep for that part instead.
Which command
| Question | Command |
|---|---|
| Can I trust glia's answers on this repo? Which boundaries can it not see? | glia health <repo> --json |
| What services are there, and how do they talk? | glia arch <repo> --json |
| Where is X? (a name, qname or fragment) | glia find <repo> X --json |
| Which files is this task, ticket or PR title about? | glia find <repo> "<text>" --files --json |
| What should I read for task T, within a token budget? | glia pack <repo> "<T>" --budget 4000 --json |
| What does this stacktrace / failing test id / diff point at? | glia resolve <repo> "<signal>" --json |
| What does changing X affect? | glia blast-radius <repo> X --json |
| What does my uncommitted change affect? A pasted diff? | glia diff-impact <repo> --json, glia diff-impact <repo> --diff <file> --json |
| How does feature Y flow, end to end? | glia trace <repo> Y --json |
| What are the entry points, and where does each go? | glia flows <repo> --json |
Which flows touch a concept (a word, not a name: refund, cache, webhook)? |
glia flows <repo> --concept refund --json |
| Which entry flows pass through X, and how deep? | glia find <repo> X --flows --json |
| What starts this code (a Dockerfile, compose service, k8s container, Procfile, systemd unit)? | glia query <repo> -e 'out(H, T) :- starts(H, T).' --json |
| Why are A and B connected? | glia why <repo> A B --json |
Who serves GET /path, or consumes topic T? |
glia serves <repo> "GET /path" --json |
| Who implements, extends or overrides X? | glia implementors <repo> X --json |
| What does X write, send or call outside the process? | glia effects <repo> X --json |
| Which tests cover X, or my change? | glia tests-for <repo> X --json, glia tests-for <repo> --base main --json |
| What did my change do to the graph? | glia delta <repo> --json |
| My change as one PR report: impact, tests, edges, new rule violations? | glia review <repo> --base main --json |
| Did my change break a client of an API or message contract? | glia contract-breaks <repo> --base main --json |
| Does the frontend's model of an API response or request match the backend's (or the OpenAPI op, or the GraphQL schema)? | glia contracts <repo> --with <backend> --fields --json |
| What usually changes along with my change? | glia cochange <repo> --base main --json |
| Are there loops between services, or import cycles? | glia cycles <repo> --json |
| Does the code break the repo's declared rules or architecture? | glia check <repo> --json |
| Which feature flags are dead, undefined, read in one place, or quiet? | glia flags <repo> --json |
| What changes often and has much depending on it? | glia hotspots <repo> --json |
| What are the tightly coupled clusters? | glia communities <repo> --json |
| What carries the most load: utilities, orchestrators, cross-service connectors? | glia hubs <repo> --json |
A structural question no command answers (every route with no handler, every call from web/ into api/)? |
glia query <repo> -e '<datalog>' --json, glia query <repo> --gql -e "MATCH ..." --json |
| Which packages, messages, contract ops or client / server models are one thing across these repos, and which copies diverged? | glia identity <repo> --with <other> --json |
| Which bazel targets build this file? | glia targets owners <repo> lib/hello-time.cc --json |
| Which build targets and test targets does my change reach? | glia targets affected <repo> --base main --json |
| What does a bazel target depend on, or what depends on it? | glia targets deps <repo> //main:hello-world --json, glia targets rdeps <repo> //lib:hello-time --json |
| Where is glia blind in this repo? | glia coverage <repo> --json |
| What could glia not pair? What looks dead? | glia gaps <repo> --json |
| Which docs govern X? | glia docs-for <repo> X --json |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · +7 lines · +12 tokens per session 433b90255af0
- 5d ago First seen · 110 lines · 182 tokens per session scan A eb8af1359135
glia is a skill published in the GitHub repository James-Chahwan/repo-graph (55 stars, last pushed 3d ago), licensed MIT. It adds 194 tokens to every session and 4,311 once invoked, about $0.0008 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.
glia compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gliaJames-Chahwan/repo-graph | Skill | 55 | 3d ago | MIT | A | 194 | Claude Code |
| sync-bridgechromium/chromium | Skill | 25k | yesterday | BSD-3-Clause | A | 109 | Claude Code, Codex |
| sync-model-processorchromium/chromium | Skill | 25k | yesterday | BSD-3-Clause | A | 98 | Claude Code, Codex |
| adversarial-revieweremdash-cms/emdash | Skill | 14k | yesterday | MIT | A | 72 | Claude Code, Codex |
| gsd-ns-reviewopen-gsd/gsd-core | Skill | 11k | yesterday | MIT | A | 16 | Claude Code |
| gitnexushashgraph-online/awesome-codex-plugins | Skill | 1.5k | yesterday | Apache-2.0 | A | 58 | Codex |
| issuejeremylongshore/tons-of-skills-marketplace | Skill | 2.9k | yesterday | MIT | A | 115 | Claude Code |