cq

cq is a skill for Claude Code, Codex from liormesh/trestle. It costs 71 tokens per session (499 once invoked), scanned A, original, MIT.

A project-context loading command called /cq, used to prepare an agent for work on a specific project. It reads the project's overview, known problems, rules, and handoff notes.

In plain words
What is it for?
Use it before coding on an existing project when you need its stored context, deployment details, conventions, or project-specific warnings.
Why use it?
It reduces the need to repeat project background and helps prevent the agent from working with the wrong assumptions.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/liormesh/trestle/cq
Any agent
npx skills add liormesh/trestle --skill cq
Clone the repo
git clone --depth 1 https://github.com/liormesh/trestle

Made for: Claude Code, Codex.

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 cq

README.md
[![agentmods](https://agentmods.dev/badge/skills/liormesh/trestle/cq.svg)](https://agentmods.dev/skills/liormesh/trestle/cq)
Your own site
<a href="https://agentmods.dev/skills/liormesh/trestle/cq"><img src="https://agentmods.dev/badge/skills/liormesh/trestle/cq.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 499 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00071 $0.00499
Opus 5 $0.00036 $0.00249
Sonnet 5 $0.00014 $0.00100
Haiku 4.5 $0.00007 $0.00050

Measured 4d ago against content hash 9dd8abc5bafe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cq 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 4d 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/cq/SKILL.md · 34 lines

What it actually says

/cq - Calling a project

/cq is the radio opening call ("seeking contact") - the user wants to tune this session into a specific project's frequency before you work. The project is: $ARGUMENTS

Load that project's context now, then confirm you're tuned in. This is the Context leg in action: pull the right context at the right moment, instead of re-briefing from scratch every session.

Steps

  1. Resolve the project. Map $ARGUMENTS to a project in the knowledge base - check MEMORY.md's active-projects list and the projects/ folder. If ambiguous or empty, list the closest matches and ask which one. Don't guess.

  2. Read its context, in this order (skip any that don't exist):

    • Handoff / resume prompt, if the project keeps one (e.g. projects/<project>/resume-prompt.md or a handoff/ doc).
    • Project overview: projects/<project>/overview.md.
    • Any project-specific gotchas, deploy notes, or state files the overview or MEMORY points to (deploy target, credential locations, known footguns).
  3. Surface the project's own rules - anything in MEMORY or the project doc that changes how you should behave on this project (where it deploys, which credential to use, conventions to respect).

  4. Run a health check if this is a coding session (per the health-check rule) - run the command in the project's ## Health Check section before writing code. Skip for read-only work.

  5. Report back, briefly:

    • What frequency we're on - project + one-line current state.
    • Live action items / open threads.
    • The gotchas you'll respect this session.
    • What you read to get there. Then ask what we're doing.

This is read-and-orient only - don't change anything until the user says what the task is.

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. 4d ago First seen · 34 lines · 71 tokens per session scan A 9dd8abc5bafe

Subscribe to this mod's changes

cq is a skill published in the GitHub repository liormesh/trestle (2 stars, last pushed 27d ago), licensed MIT. It adds 71 tokens to every session and 499 once invoked, about $0.0004 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 2026-08-31.