Borrowing it
Nothing to install: this file belongs to EastStarAI/sanad-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/EastStarAI/sanad-agent/main/.agents/skills/graphify/SKILL.mdgit clone --depth 1 https://github.com/EastStarAI/sanad-agentWrote 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/eaststarai/sanad-agent/graphify)<a href="https://agentmods.dev/skills/eaststarai/sanad-agent/graphify"><img src="https://agentmods.dev/badge/skills/eaststarai/sanad-agent/graphify.svg" alt="Measured on agentmods" 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 | $0.00059 | $0.01014 |
| Opus 5 | $0.00030 | $0.00507 |
| Sonnet 5 | $0.00012 | $0.00203 |
| Haiku 4.5 | $0.00006 | $0.00101 |
Grade A, and why
graphify 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 6d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Graphify
Use Graphify as a bounded discovery map. For code questions, verify conclusions against source files and tests; the graph may be broad or stale.
Routing
- Check for
graphify-out/graph.json. - For a natural-language codebase question with an existing graph, run one narrow graph operation before direct source search.
- Choose the smallest operation:
- One known symbol:
graphify explain "Symbol". - Relationship between two known symbols:
graphify path "A" "B". - Unknown entry point or broad concept:
graphify query "terms" --budget 800. - Reverse impact:
graphify affected "Symbol".
- One known symbol:
- After Graphify identifies likely files or symbols, use
rgand read the source/tests for the authoritative answer.
For stack traces or exact exception text, query only the top project-owned
symbols once with --budget 600, then move immediately to rg. Do not use
generic runtime names such as List, Map, String, async, or package names
as query anchors.
Read references/query.md only for query/path/explain selection, output-noise handling, or CLI fallback behavior.
Context budget and noise guard
- Default to 800 output tokens; use 600 for stack traces and at most 1500 for broad architecture work.
- Prefer exact identifiers from the request, stack trace, or repository.
- If a query reports more than 80 nodes, is truncated, or mostly returns generic language/runtime symbols, classify it as noisy. Do not paste or analyze the full traversal and do not retry with a broader query.
- On noisy output, pivot to
explain/pathfor exact symbols or continue withrgin the surfaced files. - Summarize only the few relevant nodes and source locations in the answer.
- Do not treat the presence of a node or path as proof that runtime behavior is correct. Confirm behavior in code and focused tests.
Graphify normally returns material from the corpus used to build the current graph. It can still be outside the immediate question, stale, or sourced from a previously merged/external corpus. Inspect source paths when provenance matters.
What ships with it
9 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.
- 6d ago First seen · 100 lines · 59 tokens per session scan A b04fb58692e6
graphify is a skill published in the GitHub repository EastStarAI/sanad-agent (40 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 1,014 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 2026-08-30.
Other skills, from other repositories
flutter
Flutter 3.44 — widget catalog, layouts, interactivity, animations, navigation, assets, adaptive/responsive design, accessibility, i18n, state management, data & backend (networking, serialization, Firebase, persistence), app architecture (MVVM, DI), platform integration (Android, iOS, web, Windows, macOS, Linux…
firebase-messaging
Use when setting up Firebase Cloud Messaging, managing permissions and tokens, handling background/foreground notification taps, or dispatching messages server-side (HTTP v1).
firebase-cloud-functions
Use when calling callable functions (httpsCallable), passing data to server-side logic, handling function errors/timeouts, configuring regions, or testing with the Emulator Suite.
telegram
Owner-only Telegram text bridge and Mini App gateway for the existing Ouroboros interface.
signals-migration-6-to-7
Detailed guidelines, patterns, and rules for migrating codebases from signals.dart version 6.x to version 7.x.
multi-agent-handoff
Plan and document handoffs, parent lane contracts, and parallel batch contracts between specialized AI agents (foreman, workers, reviewers). Use for multi-agent workflows, subagents, original goal preservation, native gates, claim ceilings, terminal states, baton passes, or guild-style agent coordination.