grafel-consult

grafel-consult is a skill for Claude Code from cajasmota/grafel. It costs 69 tokens per session (3,609 once invoked), scanned A, original, MIT.

An interactive skill for hiring one specialist at a time to discuss an indexed codebase. Available specialists include architects, security auditors, business analysts, performance reviewers, refactoring critics, API designers, data engineers, and quality reviewers.

In plain words
What is it for?
Use it to investigate architecture, security, business requirements, performance, refactoring, API design, data engineering, or testing questions in a codebase.
Why use it?
It gives codebase questions a focused expert perspective while keeping the selected specialist active across the conversation. It does not automatically run every specialist or save findings.

Skill for Claude Code

Written for Claude Code: when-to-use in frontmatter. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

Good fit Use it to investigate architecture, security, business requirements, performance, refactoring, API design, data engineering, or testing questions in a codebase.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cajasmota/grafel/grafel-consult
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-consult
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-consult

README.md
[![agentmods](https://agentmods.dev/badge/skills/cajasmota/grafel/grafel-consult/github.svg)](https://agentmods.dev/skills/cajasmota/grafel/grafel-consult)
Your own site
<a href="https://agentmods.dev/skills/cajasmota/grafel/grafel-consult"><img src="https://agentmods.dev/badge/skills/cajasmota/grafel/grafel-consult/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.

agentmods 80×15 button for grafel-consult

Your own site · 80×15
<a href="https://agentmods.dev/skills/cajasmota/grafel/grafel-consult"><img src="https://agentmods.dev/badge/skills/cajasmota/grafel/grafel-consult.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,609 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: 5 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 Excessive Agency · line 57
    Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.
    Fix: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops.
  • medium Rogue Agent · line 134
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Agent Snooping · line 256
    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 257
    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 258
    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 $0.00069 $0.03609
Opus 5 $0.00034 $0.01804
Sonnet 5 $0.00014 $0.00722
Haiku 4.5 $0.00007 $0.00361

Measured 10d ago against content hash a044d6dc92e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

grafel-consult 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 10d 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-consult/SKILL.md · 266 lines

How it starts

The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.

grafel-consult

Interactive consultant skill. The user hires one specialist persona at a time; that persona becomes the active consultant for the conversation and answers the user's questions using the grafel knowledge graph + generated tech docs as its primary navigation surface.

This is not an auto-fan-out skill. It does not run all 8 personas in batch. It does not produce a synthesis report. It does not auto-save findings. See docs/architecture/personas.md (v3) for the full paradigm and the reasoning behind the redesign.

Hard and soft dependencies

Dependency Type Why
/grafel-resolve Hard Orphan edges make impact-radius analysis meaningless
/grafel-tech-docs Hard Personas read module markdown to ground their answers
/grafel-business-docs Soft Business-analyst persona fidelity improves
/grafel-security-audit Soft Security-auditor persona can deduplicate against existing findings

If tech docs are missing, the skill aborts:

Tech docs not found at ~/.grafel/docs/<group>/. Run /grafel-tech-docs first, then re-invoke /grafel-consult.

CRITICAL TOOL DISCIPLINE

The active persona MUST use grafel MCP tools for ALL graph navigation. Pre-flight: call grafel_orient (view=me) first.

When to use this skill

  • "Get an architect's view of this codebase."
  • "Hire a security auditor to look at our auth flow."
  • "I want a business analyst's read on the order module."
  • "What would a performance reviewer say about this endpoint?"
  • "Review API design consistency."
  • "Check test coverage on the billing module."
  • /grafel-consult (slash command).

Flags (optional)

  • --persona <name> — hire a specific consultant directly without going through catalog selection (e.g. --persona architect).
  • --list / --catalog — print the catalog and exit.
  • --release — release the currently active consultant.
  • --switch <name> — release the current consultant and hire <name>.
  • --resume <session-id> — resume a specific saved session by ID (skips the session picker).
  • --new — force a new session, skipping the active-session list.

Read the full file on GitHub · 266 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.

  1. 10d ago First seen · 266 lines · 69 tokens per session scan A a044d6dc92e1

Subscribe to this mod's changes

grafel-consult is a skill published in the GitHub repository cajasmota/grafel (15 stars, last pushed 2d ago), licensed MIT. It adds 69 tokens to every session and 3,609 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.