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/shivaedev/pardes/claude-mdgit clone --depth 1 https://github.com/ShivaeDev/pardesWhat 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 | $0.00601 | $0.00601 |
| Opus 5 | $0.00300 | $0.00300 |
| Sonnet 5 | $0.00120 | $0.00120 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
pardes 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE
Pardes — a calm-coding marketplace of Claude Code plugins and skills. One
repo, many plugins (see README.md and .claude-plugin/marketplace.json).
Structure
.claude-plugin/marketplace.json— the plugin registry (name, owner, plugins[]).plugins/<name>/.claude-plugin/plugin.json— per-plugin manifest.plugins/<name>/{skills,agents,hooks,commands}/,.mcp.json— auto-discovered by Claude Code; no extra registration beyondplugin.json.changelog/<name>.md— per-plugin changelog (Keep a Changelog), at the repo root.
Conventions
- Owner/author in manifests is the org (
ShivaeDev), never a personal name. - No barrel files in Claude/Codex marketplace plugins; named exports; bun for everything.
plugins/pardes-pi/is a self-contained Pi extension source tree with its ownAGENTS.mdand TypeScript config. It intentionally uses bounded-contextindex.tspublic entrypoints.
One skill per plugin
Each user-facing skill ships as its own plugin (plugins/<skill>/skills/<skill>/SKILL.md),
so people install only what they want rather than swallowing a grab-bag. A plugin
generally owns exactly one skill and is named after it. Skills may still depend on
one another across plugins — the install boundary is per-skill, not per-dependency.
base is the deliberate exception: it's the home for shared hooks/infrastructure,
not a skill bundle. Don't pile new skills into base or into an existing
single-skill plugin; add a new plugin.
GitHub Actions
Two workflows ship and run, both with a security review applied — see their
inline SECURITY POSTURE / NOTE comment blocks before changing them:
lint.yml— runsbiome cion PRs (and pushes tomainas a backstop). Read-only token. To actually block merge it must be a required status check in the repo ruleset (a repo setting, not YAML).version-bump.yml— auto-bumps plugin versions onpush:mainonly (nopull_request/workflow_dispatch, so nothing untrusted ever runs with the token). Opens a PR, merges it synchronously, then tags the merged commit; version tags are create-only via a*--v*ruleset.
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 · 49 lines · 601 tokens per session scan A 0437371dae6f
pardes CLAUDE.md is an instructions file published in the GitHub repository ShivaeDev/pardes (5 stars, last pushed 1mo ago), licensed MIT. It adds 601 tokens to every session, about $0.0030 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
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.
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).
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.