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 cajasmota/grafel --skill grafel-graph-readgit clone --depth 1 https://github.com/cajasmota/grafelWrote 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/cajasmota/grafel/grafel-graph-read)<a href="https://agentmods.dev/skills/cajasmota/grafel/grafel-graph-read"><img src="https://agentmods.dev/badge/skills/cajasmota/grafel/grafel-graph-read/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/cajasmota/grafel/grafel-graph-read"><img src="https://agentmods.dev/badge/skills/cajasmota/grafel/grafel-graph-read.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 | $0.00028 | $0.00691 |
| Opus 5 | $0.00014 | $0.00345 |
| Sonnet 5 | $0.00006 | $0.00138 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade A, and why
grafel-graph-read 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 9d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
READ Protocol
Step 1 — status
Call grafel_orient (view=me) first. Confirms the group name and which repos are indexed. If no graph is loaded, ask the user to run grafel index <path> first.
Step 2 — inspect
For each entity of interest (a class, function, file path the user named):
grafel_inspect entity_id=<id-or-path>returns the entity + 1-hop neighbors with line-precise CALLS/called_by edgescalls[].line= line in the inspected entity's body where the outbound call appearscalled_by[].line+called_by[].context= line and ~40-char snippet in the caller's bodydiscriminators[](#2666) — when the entity doesvar === literalcomparisons (e.g.checklistType === 2), each row carries{file_line, literal, other_side}so you can jump straight to the comparison without scanning the body. Discriminator literals are also mixed into the BM25 doc terms, sografel_findqueries like "checklistType 2" surface the enclosing entity.- Use these to pinpoint call sites without calling
get_source - Look at the neighbors for ORIENTATION before drilling deeper
Step 3 — expand
When you need to traverse:
grafel_subgraph entity_id=<id> edge=CALLS direction=incomingfor callersgrafel_subgraph entity_id=<id> edge=CALLS direction=outgoingfor calleesgrafel_find name=<substring>if you don't have an id yet
Other useful read tools to layer in: grafel_trace (process-flow BFS), grafel_cross_links (HTTP/Kafka/WS cross-repo), grafel_orient (view=clusters) (Louvain communities), grafel_orient (view=modules), grafel_subgraph.
In-app navigation (#2665)
For Expo Router / React Navigation / Next.js push-sites, two shortcuts fold the NAVIGATES_TO graph into the existing read tools:
grafel_endpoints(kind="navigation")— list distinct routes, with mergedparams_keys(sorted, deduped JSON array) per route. Use this to answer "which screens take param X?".grafel_related(direction="callers", "/route/literal")— pass a literal beginning with/; the handler reverse-traverses NAVIGATES_TO and returns push-site callers withfile,line, and per-callparams_keys. Use this when adding a required param: callers whoseparams_keysis missing the new key are the diff candidates.
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.
- 9d ago First seen · 38 lines · 28 tokens per session scan A 442891af4d1f
grafel-graph-read is a skill published in the GitHub repository cajasmota/grafel (14 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 691 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…