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 instructions/doublej/consult-user-mcp/agents-mdgit clone --depth 1 https://github.com/doublej/consult-user-mcpWrote 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/instructions/doublej/consult-user-mcp/agents-md)<a href="https://agentmods.dev/instructions/doublej/consult-user-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/doublej/consult-user-mcp/agents-md.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 | $0.01761 | $0.01761 |
| Opus 5 | $0.00881 | $0.00881 |
| Sonnet 5 | $0.00352 | $0.00352 |
| Haiku 4.5 | $0.00176 | $0.00176 |
Grade C, and why
consult-user-mcp AGENTS.md scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf directory # NOT: rm -r directory This is a copy
59% identical to dspy-skills AGENTS.md — 151 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
This project uses bd (beads) for issue tracking. Run bd prime for full workflow context.
Architecture in one line: Issues live in a local Dolt database (
.beads/dolt/); cross-machine sync usesbd dolt push/pull(a git-compatible protocol), stored underrefs/dolt/dataon your git remote — separate fromrefs/heads/*where your code lives..beads/issues.jsonlis a passive export, not the wire protocol.See SYNC_CONCEPTS.md for the one-screen overview and anti-patterns (don't treat JSONL as the source of truth; don't
bd importduring normal operation; don't reach for third-party Dolt hosting before trying the default).
Quick Reference
bd ready # Find available work
bd show <id> # View issue details
bd update <id> --claim # Claim work atomically
bd close <id> # Complete work
bd dolt push # Push beads data to remote
Verification
Run the suites in the macOS container. bun run test:container, or a
subset with SUITES="unit layout" bun run test:container. Setup, knobs and
gotchas: container/README.md.
bun run test:container # everything, in the VM — the verdict
bun test # mcp-server tests (anywhere)
bun run test:layout # clipping, overlap, text-fit (anywhere — off-screen)
bun run test:visual # screenshot + OCR per fixture ⚠ container
bun run test:keyboard # the keyboard contract ⚠ container
The two marked ⚠ spawn a real dialog per case. On a machine somebody is using
they take the screen and the keyboard for minutes, and any focus change
corrupts the result silently — the visual suite spent months photographing one
stuck window and reporting OK. test:layout is the exception: it renders
off-display, so it is safe anywhere and it is the one that fails a build.
A green layout run is not a clean surface. It waives every state with a known
open bug and prints a NOT VOUCHED FOR line naming them. Read it.
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 · 156 lines · 1,761 tokens per session scan C 690361760ae7
consult-user-mcp AGENTS.md is an instructions file published in the GitHub repository doublej/consult-user-mcp (40 stars, last pushed 15d ago), licensed MIT. It adds 1,761 tokens to every session, about $0.0088 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). It is 59% identical to dspy-skills AGENTS.md, differing in 151 lines, and is treated as a copy.
Other instructions, from other repositories
spec-kitty AGENTS.md
AGENTS.md instructions for Priivacy-ai/spec-kitty, covering spec kitty development guidelines, ⚠️ critical: load the project charter first, ⚠️ critical: template source location, ⚠️ critical: use canonical sources, never improvise and ⚠️ critical: git workflow — no direct pushes to origin/main.
coral CLAUDE.md
Instructions for cdknorow/coral, covering claude.md - coral go, mission, testing, go unit tests and legacy parity tools (historical reference).
gemini-cli-desktop AGENTS.md
Instructions for Piebald-AI/gemini-cli-desktop, a project described as: Web/desktop UI for Gemini CLI/Qwen Code. Manage projects, switch between tools, search across past conversations, and manage MCP servers, all from one multilingual interface, locally or remotely.
sessionview AGENTS.md
Instructions for tyql688/sessionview, covering sessionview, commands, app / frontend, gates must pass under both feature sets: default (gui) and and --no-default-features --features headless.
SubFrame AGENTS.md
Instructions for Codename-11/SubFrame, covering subframe - subframe project, core working principle, relationship to native ai tools, session start and concurrent work & worktrees.
codmate AGENTS.md
Instructions for loocor/codmate, a project described as: CodMate is a macOS SwiftUI app for managing CLI AI sessions: browse, search, organize, resume, and review work produced by Codex, Claude Code, and Gemini CLI. It focuses on speed, a compact three-column UI, and “ship it” workflows like Project Review (Git…