agentmods.dev

grafel-tech-docs

grafel-tech-docs is a skill for Claude Code from cajasmota/grafel. It costs 70 tokens per session (2,269 once invoked), scanned A, original, MIT.

A tool for generating detailed technical documentation from a codebase registered with grafel, a system that maps code relationships. It creates module documentation, API references, cross-project links, and recurring-pattern notes.

In plain words
What is it for?
Use it to document modules, APIs, shared concerns, relationships between repositories, and established code patterns for engineers.
Why use it?
It reduces the need for engineers to trace dependencies and understand many files manually. It can also rerun documentation for changed parts of the codebase.

Skill for Claude Code

Written for Claude Code: when-to-use in frontmatter. Also seen: mentions subagents.

not rated 13repo +1 today A scan SkillSpector: warn 70 tokens original MIT

Good fit Use it to document modules, APIs, shared concerns, relationships between repositories, and established code patterns for engineers.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cajasmota/grafel/grafel-tech-docs
View source ↗ cajasmota/grafel
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 cajasmota/grafel --skill grafel-tech-docs
Clone the repo
git clone --depth 1 https://github.com/cajasmota/grafel

Made for: Claude Code.

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.

agentmods badge for grafel-tech-docs

README.md
[![agentmods](https://agentmods.dev/badge/skills/cajasmota/grafel/grafel-tech-docs.svg)](https://agentmods.dev/skills/cajasmota/grafel/grafel-tech-docs)
Your own site
<a href="https://agentmods.dev/skills/cajasmota/grafel/grafel-tech-docs"><img src="https://agentmods.dev/badge/skills/cajasmota/grafel/grafel-tech-docs.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,269 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 4 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 130
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 131
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 132
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 133
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
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 5.1 $0.00070 $0.02269
Opus 5 $0.00035 $0.01135
Sonnet 5 $0.00014 $0.00454
Haiku 4.5 $0.00007 $0.00227

Measured 8d ago against content hash 7c3ece3dadd7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

grafel-tech-docs 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 8d 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.

skills/grafel-tech-docs/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

grafel-tech-docs

Generate the complete technical documentation set for a registered grafel group: per-module READMEs, API reference, cross-cutting concerns, group synthesis, cross-repo links, and pattern library.

This skill is a direct extraction of the technical tier (Passes 0–12 + Pass 20) from /generate-docs. It is the largest and most expensive skill in the grafel family.

CRITICAL TOOL DISCIPLINE (enforced on every pass — read before ANY action)

For ANY question about "what entities/files exist in this codebase", "who calls X", "what does Y import", "what's in module Z", you MUST use grafel MCP tools: grafel_inspect, grafel_find, grafel_subgraph, grafel_orient (view=overview), grafel_orient (view=clusters), grafel_trace, grafel_orient (view=me).

You are STRICTLY FORBIDDEN from using find/ls/wc/grep on the codebase for entity discovery. Use Bash ONLY for reading specific source line ranges that grafel_get_source returns, running grafel docgen --llm-mode=apply, and writing output files into the staging directory.

If the MCP returns empty or seems wrong, file a side ticket and ABORT — do NOT silently substitute grep results for graph queries.

Pre-flight assertion (FIRST action in every pass)

Call grafel_orient (view=me) before doing anything else. If it errors: ABORT with "grafel MCP not configured for this directory. Run /mcp to fix, then re-invoke /grafel-tech-docs."

When to use this skill

Invoke when the user asks for any of:

  • "Document this repo / this group."
  • "Regenerate the docs after the recent refactor."
  • "Write API reference / module guide / cross-repo overview."
  • "Fill the LLM bundle" / "run docgen in LLM mode" / "orchestrate the bundle."

Do not invoke it for business-tier docs (that is /grafel-business-docs), enrichment (that is /grafel-graph-enrich), or residual cleanup (that is /grafel-resolve).

Prerequisites

  • A running grafel daemon (grafel status should show "running").
  • A resolved grafel group.
  • Per-repo <repo>/.grafel/graph.json from the most recent index run.
  • Recommended (not required): run /grafel-resolve first to minimize residual edges. Run /grafel-graph-quality to confirm the graph foundation is solid before spending tokens on writing.

Read the full file on GitHub · 142 lines

Files

What ships with it

57 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.

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. 8d ago First seen · 142 lines · 70 tokens per session scan A 7c3ece3dadd7

Subscribe to this mod's changes

grafel-tech-docs is a skill published in the GitHub repository cajasmota/grafel (13 stars, last pushed today), licensed MIT. It adds 70 tokens to every session and 2,269 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.

Writing and docs
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens