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/sublang-ai/cligent/claude-mdgit clone --depth 1 https://github.com/sublang-ai/cligentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/sublang-ai/cligent/claude-md)<a href="https://agentmods.dev/instructions/sublang-ai/cligent/claude-md"><img src="https://agentmods.dev/badge/instructions/sublang-ai/cligent/claude-md.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00326 | $0.00326 |
| Opus 5 | $0.00163 | $0.00163 |
| Sonnet 5 | $0.00065 | $0.00065 |
| Haiku 4.5 | $0.00033 | $0.00033 |
Grade A, and why
cligent 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 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.
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
92% identical to cligent AGENTS.md — 5 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
CLAUDE
Specs (Source of Truth)
- Canonical specs live in @specs/. Start with @specs/map.md for a quick-reference index and @specs/meta.md for the spec format; spec packages live in @specs/packages.
- Before making changes or suggestions in an area that has a spec, read the relevant spec file(s) first and follow them.
- Whenever your changes involve any spec, or you make a decision worth recording, keep the specs in sync — don't let them drift.
- Resolve conflicts spec-first, then iterate freely: an intended change that conflicts with existing spec items is resolved in the specs — or dropped — before coding against it; implementing first to explore an approach is fine, and implementation lessons update this intent's specs, but no intent completes until its specs and code agree.
- Keep specs lawful per @specs/meta.md — the law itself, not this summary: complete and exact (meta-34), minimal (meta-23), one requirement per item (meta-29), cohesive packages for a shared intent (meta-13), sections per meta-30, relationships and test evidence only as inline citations (meta-14, meta-16, meta-20), integration/system tests only (meta-21, meta-32).
- Run
spex lintto check structure, item IDs, and citations after editing specs; never add trace lines to satisfy an older checker.
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 · 15 lines · 326 tokens per session scan A c15cf8d360c7
cligent CLAUDE.md is an instructions file published in the GitHub repository sublang-ai/cligent (52 stars, last pushed 5d ago), licensed Apache-2.0. It adds 326 tokens to every session, about $0.0016 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to cligent AGENTS.md, differing in 5 lines, and is treated as a copy.
Other instructions, from other repositories
obsidian-mind CLAUDE.md
Claude Code instructions for breferrari/obsidian-mind, covering obsidian mind, skills & capabilities, custom slash commands, vault structure and obsidian cli.
obsidian-mind AGENTS.md
AGENTS.md instructions for breferrari/obsidian-mind, covering obsidian mind, hooks, commands, memory and reaching this vault from another repo.
parallel-code CLAUDE.md
Instructions for johannesjo/parallel-code, covering parallel code, stack, commands, project structure and conventions.
neo4j-skills AGENTS.md
Instructions for neo4j-contrib/neo4j-skills, covering writing skills for this repository, language style — write for agents, not humans, six design principles, skill.md spec (agentskills.io) and frontmatter.
switchback-running CLAUDE.md
Instructions for rlacombe/switchback-running, covering ultrarunning training companion, constitution, athlete data, training philosophy and core principles.
SubFrame AGENTS.md
Instructions for Codename-11/SubFrame, covering subframe - subframe project, core working principle, relationship to native ai tools, session start and concurrent work & worktrees.