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/kreek/consult/claude-mdgit clone --depth 1 https://github.com/kreek/consultWrote 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/kreek/consult/claude-md)<a href="https://agentmods.dev/instructions/kreek/consult/claude-md"><img src="https://agentmods.dev/badge/instructions/kreek/consult/claude-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 | $0.00295 | $0.00295 |
| Opus 5 | $0.00148 | $0.00148 |
| Sonnet 5 | $0.00059 | $0.00059 |
| Haiku 4.5 | $0.00030 | $0.00030 |
Grade A, and why
consult CLAUDE.md 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
CLAUDE.md
This file provides Claude-specific guidance for working on Consult. The main
portable maintainer instructions live in AGENTS.md; follow that file for repo
layout, validation, skill anatomy, versioning, and release rules.
Pi self-improvement source access
Pi can inspect its own installed package when runtime behavior, extension APIs, or self-improvement work depends on Pi internals. Treat that package as a read-only upstream source: read it to confirm current APIs and behavior, but make Consult changes in this repository unless the user explicitly asks to work on Pi itself.
For most npm-style installs, find Pi's package with:
npm root -g
Then look under @earendil-works/pi-coding-agent in that global
node_modules directory. Package-manager installs usually place the same global
node_modules tree under the manager prefix, for example
<prefix>/lib/node_modules/@earendil-works/pi-coding-agent. Do not hard-code a
machine-specific absolute path in repo docs or committed code. Resolve it at
runtime with npm root -g, which pi, or the package manager's prefix command.
Useful read-only entry points are the package README.md, docs/, examples/,
package.json, and exported type declarations. Follow linked docs before
changing Consult extensions that depend on Pi APIs.
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 · 31 lines · 295 tokens per session scan A 4e12aacbfb43
consult CLAUDE.md is an instructions file published in the GitHub repository kreek/consult (1 stars, last pushed yesterday), licensed MIT. It adds 295 tokens to every session, about $0.0015 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 instructions, from other repositories
socket AGENTS.md
AGENTS.md instructions for gaelic-ghost/socket, covering agents.md, repository scope, what this file covers, where to look first and working rules.
jig AGENTS.md
AGENTS.md instructions for ramboz/jig, covering jig — ai-native dev scaffold, hot cache, project codenames / active work, key terms (one-line index — full defs via /jig:explain ) and key documents.
jig CLAUDE.md
Claude Code instructions for ramboz/jig, covering jig — ai-native dev scaffold, hot cache, project codenames / active work, key terms (one-line index — full defs via /jig:explain ) and key documents.
toolshed CLAUDE.md
Claude Code instructions for knitli/toolshed, covering claude.md, what this is, commands, architecture and version sync.
modellix-plugin AGENTS.md
AGENTS.md instructions for Modellix/modellix-plugin, covering agents.md, project overview, agent plugins 1.0.0 core and host adapters, sources of truth and language.
llm-redact CLAUDE.md
Claude Code instructions for asanderson/llm-redact, covering claude.md, project purpose, commands, architecture and testing conventions.