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.
npx agentmods add skills/liormesh/trestle/cqnpx skills add liormesh/trestle --skill cqgit clone --depth 1 https://github.com/liormesh/trestleWrote 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/liormesh/trestle/cq)<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>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 | $0.00071 | $0.00499 |
| Opus 5 | $0.00036 | $0.00249 |
| Sonnet 5 | $0.00014 | $0.00100 |
| Haiku 4.5 | $0.00007 | $0.00050 |
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.
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
-
Resolve the project. Map
$ARGUMENTSto a project in the knowledge base - check MEMORY.md's active-projects list and theprojects/folder. If ambiguous or empty, list the closest matches and ask which one. Don't guess. -
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.mdor ahandoff/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).
- Handoff / resume prompt, if the project keeps one (e.g.
-
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).
-
Run a health check if this is a coding session (per the health-check rule) - run the command in the project's
## Health Checksection before writing code. Skip for read-only work. -
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.
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.
- 4d ago First seen · 34 lines · 71 tokens per session scan A 9dd8abc5bafe
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.
Other skills, from other repositories
project-sync
On-demand AI-powered sync of a project's repo state into the brain vault. Reads live git/GitHub/Jira data, updates the project status doc, and makes targeted edits to relevant brain docs where content is clearly stale. Triggered by "/project-sync [name]", "sync [project]", "what's the current state of [project]".
triage-tasks
Use when you want to review and batch-update open vault task statuses for the current project or across all projects.
tackle-task
Use when starting work on a specific vault task, when a task title or path is mentioned, or when coming from triage output.
add-task
Use when you want to quickly capture a new task in the vault from a title, with optional priority and due date.
log-decision
Log cross-cutting business/product/hiring/vendor decisions to decisions/ directory with context and alternatives.
mxInitProject
Use when the user says "/mxInitProject", "bootstrap project", "init project", "setup ai config", "initialize claude config", "scaffold project", or otherwise wants to bootstrap a new repository with the mxLore AI-documentation structure (CLAUDE.md, docs/ layout, optional MCP project registration). Idempotent — safe to…