Borrowing it
Nothing to install: this file belongs to Koroqe/OPOS. 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/Koroqe/OPOS/main/.claude/skills/consult-agent/SKILL.mdgit clone --depth 1 https://github.com/Koroqe/OPOSWrote 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/koroqe/opos/consult-agent)<a href="https://agentmods.dev/skills/koroqe/opos/consult-agent"><img src="https://agentmods.dev/badge/skills/koroqe/opos/consult-agent/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/koroqe/opos/consult-agent"><img src="https://agentmods.dev/badge/skills/koroqe/opos/consult-agent.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 | $0.01313 |
| Opus 5.5 | $0.00011 | $0.00525 |
| Sonnet 5.5 | $0.00006 | $0.00263 |
| Haiku 4.5 | $0.00003 | $0.00131 |
Grade A, and why
consult-agent 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 1mo 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
consult-agent
When to use
Any time a skill or agent needs the perspective / judgment of another agent without invoking the full agent runtime. This canonicalizes the "spawn general-purpose and frame it as <agent> reading its own definition" pattern used ad-hoc in design-process and the R&D survey.
Use this when:
- A skill needs cross-functional input (e.g.
design-processstep 4 — consulting dept leads). - An agent needs another agent's view on a tradeoff before deciding.
- A multi-agent design session benefits from a "second opinion."
Do NOT use this when:
- The caller IS the agent in question (no self-consultation; that's just thinking).
- The information being asked is in the agent's
.mdfile verbatim and can be read directly (no need to spawn a subagent for that).
Inputs
agent_name— the kebab-casename:of the agent to consult (e.g.eng-lead). Required.question— the consultation prompt as free text. Required.context— optional extra background to include in the subagent's system prompt (e.g. the relevant code excerpts, the user's framing). Defaults to empty.
Steps
-
Locate the agent definition. Glob
.claude/agents/**/*.mdfor a file whose frontmatter containsname: <agent_name>. If zero matches → error ("agent not found"). If multiple matches → error ("ambiguous agent name; specify path"). The recursive glob handles both flat.claude/agents/*.mdand nested.claude/agents/<dept>/<role>.mdlayouts. -
Read the agent's full definition file. Capture both frontmatter and body.
-
Read the agent's department charter for context. Special-case
department: company: readcompany/CLAUDE.md.jinja(orcompany/CLAUDE.mdif rendered in a consumer scaffold) — there is NOdepartments/company/folder. The 4 company-tier agents (ceo,coo,chief-of-staff,ops-manager) all use the company-scope charter. For all other departments: readdepartments/<name>/CLAUDE.md. If the charter file is missing for a dept-scoped agent: soft-fail (proceed without charter content; log a warning in the history-entry body).
What ships with it
2 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.
- 1mo ago Changed 64edb848e818
- 1mo ago First seen · 79 lines · 28 tokens per session scan A f448e9bcb8f1
consult-agent is a skill published in the GitHub repository Koroqe/OPOS (4 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 1,313 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
super-evolve
Ultimate self-evolution skill. Merges evolve + self-improve into one comprehensive meta-skill with external research, area focus, dry-run mode, and expanded memory mining.
pr-to-video
Turn a GitHub pull request (a PR URL, owner/repo#N, or 'this PR' in a checked-out repo) into a code-change explainer video — changelog, feature reveal, fix, or refactor walkthrough built from the diff, commits, and files: the input is a code change, not a website. Not a product promo (/product-launch-video) or a no-PR…
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
motion-graphics
Use when creating a short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline…
glass-shard-title
Glass shards fly in through fog and tile themselves into the headline. HyperFrames block, 1920×1080, 12.16s, 19 variables.
torchforge-rl-training
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.