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/pactkit/claude-code-plugin/claude-mdgit clone --depth 1 https://github.com/pactkit/claude-code-pluginWhat 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 | $0.10265 | $0.10265 |
| Opus 5 | $0.05132 | $0.05132 |
| Sonnet 5 | $0.02053 | $0.02053 |
| Haiku 4.5 | $0.01026 | $0.01026 |
Grade A, and why
claude-code-plugin 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 yesterday.
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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- yesterday First seen · 792 lines · 10,265 tokens per session scan A b8391b7d61b0
claude-code-plugin CLAUDE.md is an instructions file published in the GitHub repository pactkit/claude-code-plugin (5 stars, last pushed 2d ago), with no licence file. It adds 10,265 tokens to every session, about $0.0513 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-driven-steroids AGENTS.md
Instructions for lindoelio/spec-driven-steroids, covering agents.md, project identity, technology stack, essential commands and agent constraints.
mstar-harness CLAUDE.md
Instructions for btspoony/mstar-harness, a project described as: An omni-plugin for harness engineering workflows with multi-agents, programmatic gates and skills.
joycraft AGENTS.md
Instructions for maksutovic/joycraft, covering joycraft, behavioral boundaries, always, ask first and never.
ai-workflow-kit CLAUDE.md
Instructions for silver2dream/ai-workflow-kit, covering claude.md (principal agent guide), role: principal engineer, project overview, rule routing (important) and kit core rules (always).
planr-pipeline CLAUDE.md
Instructions for openplanr/planr-pipeline, covering planr-pipeline — agile planning & implementation guide, context-gathering protocol, step 1: read the task list, step 2: read the parent chain (mandatory) and step 3: read architecture context.
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.