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/kevinelliott/agentpipe/claude-mdgit clone --depth 1 https://github.com/kevinelliott/agentpipeWhat 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 | $0.02572 | $0.02572 |
| Opus 5 | $0.01286 | $0.01286 |
| Sonnet 5 | $0.00514 | $0.00514 |
| Haiku 4.5 | $0.00257 | $0.00257 |
Grade A, and why
agentpipe 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 2d 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentPipe Project Memory
Project Overview
AgentPipe is a CLI and TUI application that orchestrates conversations between multiple AI agent CLIs (Claude, Gemini, Qwen, Codex, Ollama). It allows different AI tools to communicate in a shared "room" with various conversation modes.
Key Technical Details
Go Version
- IMPORTANT: Requires Go 1.24+ (go.mod specifies 1.24.0)
- GitHub Actions workflows must use Go 1.24
- All dependencies are compatible with Go 1.24
Health Check Configuration
- Default timeout: 5 seconds (increased from 2 seconds)
- Claude CLI needs longer startup time
- Flag:
--health-check-timeoutto customize - Flag:
--skip-health-checkto bypass
Directory Structure
- Chat logs:
~/.agentpipe/chats/(default) - Homebrew formula:
Formula/(NOT Formulae/) - Config examples:
examples/
CI/CD Configuration
Linting
- Use golangci-lint-action@v6 with golangci-lint v1.x (latest stable)
- GitHub Action version parameter:
version: latest(downloads latest v1.x) - IMPORTANT: Config file (
.golangci.yml) uses v1.x format (no version field) - Note: Removed
nakedretlinter (removed in v2.x, compatible with v1.x) - Status: v2.x requires config schema changes; staying on v1.x is more stable
- Local linting: Install latest golangci-lint v1.x
- Install:
brew install golangci-lint - Or:
go install github.com/golangci/golangci-lint/cmd/golangci-lint@latest
- Install:
- Configuration structure:
linters-settings:for linter config,issues.exclude-rules:for exclusions - Cognitive complexity threshold: 30
- Excluded from complexity checks: pkg/tui/, pkg/adapters/, pkg/orchestrator/
Testing
- Windows test fix: Single-line command (no multiline)
- Command:
go test -v -race ./... - No coverage profile to avoid Windows parsing issues
Releases
- Triggered on tags:
v[0-9]+.[0-9]+.[0-9]+ - Requires
HOMEBREW_TAP_TOKENsecret for formula updates - Token needs
reposcope for cross-repo access
Common Issues & Fixes
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.
- 2d ago First seen · 219 lines · 2,572 tokens per session scan A 031efb85a9e2
agentpipe CLAUDE.md is an instructions file published in the GitHub repository kevinelliott/agentpipe (148 stars, last pushed 2mo ago), licensed MIT. It adds 2,572 tokens to every session, about $0.0129 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 2026-08-30.
Other instructions, from other repositories
cognirepo CLAUDE.md
Instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
cognirepo copilot-instructions.md
Instructions for ashlesh-t/cognirepo, covering cognirepo — github copilot instructions, session start (call in this order every session), tool routing, behaviour rules and fallback rules.
gemini-simplify-extension GEMINI.md
Gemini CLI instructions for JhonatanRian/gemini-simplify-extension, covering gemini simplify — extension context, available command, available sub-agents, workflow and rules.
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.
trellis AGENTS.md
Instructions for craigcossairt/trellis, covering agents.md , project, what i need from agents, current state - source of truth pointers and tech stack.