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/marcus/sidecar/claude-mdgit clone --depth 1 https://github.com/marcus/sidecarWhat 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 | $0.00005 | $0.00005 |
| Opus 5 | $0.00003 | $0.00003 |
| Sonnet 5 | $0.00001 | $0.00001 |
| Haiku 4.5 | $0.00001 | $0.00001 |
Grade A, and why
sidecar 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.
This is a copy
100% identical to deepseek-harness CLAUDE.md — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
@AGENTS.md
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 · 2 lines · 5 tokens per session scan A 336cc4fbf19b
sidecar CLAUDE.md is an instructions file published in the GitHub repository marcus/sidecar (1,049 stars, last pushed 2d ago), licensed MIT. It adds 5 tokens to every session, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to deepseek-harness CLAUDE.md, differing in 3 lines, and is treated as a copy.
Other instructions, from other repositories
flow CLAUDE.md
Instructions for AixleHQ/flow, covering claude.md, documentation index, before pushing a branch or opening/updating a pr, docker is required and test parallelization.
aegis AGENTS.md
Instructions for apiad/aegis, covering agents, running, know-how, package management and layout.
Lorekeeper copilot-instructions.md
Instructions for Jessinra/Lorekeeper, covering lorekeeper copilot code review instructions, review severity tiers, conventional comments format, lorekeeper architecture constraints and core invariants.
vichu-flow AGENTS.md
Instructions for corteshvictor/vichu-flow, covering agent instructions, project overview, git, build, test, and the quality gate and conventions.
ghbrk CLAUDE.md
Instructions for marconae/ghbrk, covering claude.md — ghbrk development rules, git commits and dependencies.
Lorekeeper python.instructions.md
Instructions for Jessinra/Lorekeeper, covering python / lorekeeper guidelines, scope, review focus, project conventions and repo-specific red flags.