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/zevtos/agentpipe/claude-mdgit clone --depth 1 https://github.com/zevtos/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 | $0.03319 | $0.03319 |
| Opus 5 | $0.01659 | $0.01659 |
| Sonnet 5 | $0.00664 | $0.00664 |
| Haiku 4.5 | $0.00332 | $0.00332 |
Grade A, and why
agentpipe CLAUDE.md scanned grade A 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **External-Inclusion Bar (what the `god` preset may install).** Tier A = agentpipe's own content (always OK). Tier B = an *official, vendor-backed* tool installed via a channel the user already trusts (OS pkg manager / How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agentpipe
Gated pipeline orchestration for Claude Code and Codex CLI: specialist agents, slash commands, and skills.
9 agents, 16 commands, 3 skills (gost-report, doc2kb, ultrasearch), 19 research docs. Multi-target installer:
default puts everything in ~/.claude/; --target codex puts skills in ~/.codex/skills/
and skips agents/commands (Codex format differences).
The only build step is packaging skills into release zips — no runtime, no tests, no dependencies.
Commands
bash install.sh # install for Claude Code (default)
bash install.sh --target codex # install for Codex CLI (skills only)
bash install.sh --dry # preview what would change (works with --target too)
bash install.sh --diff # show repo vs installed differences
bash install.sh --pull # copy installed back to repo
bash install.sh --update # git pull --ff-only, then install (alias of update.sh)
bash install.sh --uninstall # remove installed files (target-scoped)
bash update.sh # canonical update entry point (forwards to install.sh --update)
bash install.sh --no-claude-md # skip baseline CLAUDE.md (default: install-if-missing)
bash install.sh --skills-only # update only skills/*, skip agents/commands/hooks (works with --target)
bash install.sh --with-sound-hooks # opt-in: Stop sound hook only (one beep per turn)
bash install.sh --with-notification-sound # opt-in: Claude Notification sound hook only
bash install.sh --clean-sound-hooks # strip all sound hooks (Stop+Notification) from settings/hooks config
bash install.sh --with-thinking-summaries # opt-in: showThinkingSummaries=true
bash install.sh --model-profile opus # all agents on opus (default: mixed; persisted to settings.json)
bash scripts/build-skills.sh # package every skills/<name>/ into dist/<name>.zip
bash scripts/eval.sh --list # list local agent eval scenarios (no claude calls)
bash scripts/eval.sh <agent> # run agent prompt-quality eval (uses claude -p, ~2 msgs/scenario)
python3 scripts/validate-skills.py # enforce 1024-byte limit on every skills/*/SKILL.md description
python3 scripts/validate-repo.py # check docs-vs-disk count drift + agent/command/skill frontmatter
git config core.hooksPath scripts/git-hooks # one-time per clone: enable repo pre-commit hooks
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.
- 3d ago First seen · 186 lines · 3,319 tokens per session scan A 225f1c4d2f0c
agentpipe CLAUDE.md is an instructions file published in the GitHub repository zevtos/agentpipe (11 stars, last pushed 2mo ago), licensed MIT. It adds 3,319 tokens to every session, about $0.0166 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.