Borrowing it
Nothing to install: this file belongs to cajasmota/grafel. 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/cajasmota/grafel/main/.cursor/commands/grafel-consult.mdgit 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/commands/cajasmota/grafel/grafel-consult)<a href="https://agentmods.dev/commands/cajasmota/grafel/grafel-consult"><img src="https://agentmods.dev/badge/commands/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.
<a href="https://agentmods.dev/commands/cajasmota/grafel/grafel-consult"><img src="https://agentmods.dev/badge/commands/cajasmota/grafel/grafel-consult.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 | $0.00063 | $0.00762 |
| Opus 5 | $0.00032 | $0.00381 |
| Sonnet 5 | $0.00013 | $0.00152 |
| Haiku 4.5 | $0.00006 | $0.00076 |
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 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/grafel-consult (Cursor)
Cursor wrapper for the canonical grafel-consult skill. Persona bodies live at skills/grafel-consult/personas/*.md in the grafel source tree and are referenced (not duplicated) here.
Where this runs
- Chat panel (inline): the slash command activates a persona by inlining its body into the current chat. One active consultant per chat thread.
- Agents Window: hiring a consultant can open a new agent tab, giving per-tab isolation. Recommended when you want multiple consultants alive simultaneously across tabs.
Either way, the persona body is the system prompt.
Steps
1. Pre-flight
- Call
grafel_whoami. If unavailable, ask the user to run/grafel-statusand abort. - Verify
~/.grafel/docs/<group>/modules/exists. If not, abort with:Tech docs not found. Run
/grafel-tech-docsfirst, then re-invoke/grafel-consult.
2. Catalog
Read every file in skills/grafel-consult/personas/*.md. Extract name: and description: from frontmatter and present a numbered list. Also scan ~/.claude/agents/grafel-*.md for user-defined personas (Cursor reads these by convention when present).
3. Hire
Ask the user which consultant to hire — by name or by problem description. If by problem description, recommend a match and confirm.
4. Activate
- Chat panel: inline the persona body as a system-style turn (
You are now grafel-<name>. <full body>). Announce activation. Subsequent turns use this persona. - Agents Window: open a new agent tab with the persona body as system prompt. Pass the user's original question as the first user turn.
Run the persona's READ instructions once at activation to ground.
5. Converse
The active consultant answers using grafel MCP tools + tech docs + the Communication styles declared in its body. No fixed response shape.
6. Consult-Out
When the persona emits a [CONSULT-OUT] callout and the user approves:
- Chat panel: load the peer's body, answer the sub-question with the peer's lens for this turn only, prefix with
[CONSULT-IN: <peer>]. Then revert to the original consultant. - Agents Window: open a new tab for the peer with carry-over context. Read the peer's answer manually and bring it back.
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 · 67 lines · 63 tokens per session scan A 1ad53ee3f66f
grafel-consult is a command published in the GitHub repository cajasmota/grafel (14 stars, last pushed today), licensed MIT. It adds 63 tokens to every session and 762 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
argos
A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.