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/disruptionjoe/caret/agents-mdgit clone --depth 1 https://github.com/disruptionjoe/caretWrote 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/disruptionjoe/caret/agents-md)<a href="https://agentmods.dev/instructions/disruptionjoe/caret/agents-md"><img src="https://agentmods.dev/badge/instructions/disruptionjoe/caret/agents-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 | $0.00458 | $0.00458 |
| Opus 5 | $0.00229 | $0.00229 |
| Sonnet 5 | $0.00092 | $0.00092 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
caret AGENTS.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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This repo rebuilds from the cheatsheet outward.
Source Of Truth Order
Use this order when interpreting or editing the repo:
/caret-cheatsheet.md/notation/SPEC.md/notation/SEMANTICS.md/notation/INTERPRETATION.md/notation/SECURITY.md/notation/DECISIONS.md
If a downstream file conflicts with that order, the downstream file is wrong.
Repo Supremacy
This repo's live canon outranks:
- archived repo material
- drafts
- research notes
- imported examples
- external repos
- older task files or legacy skill files
If outside or legacy material conflicts with the current repo canon, treat that material as stale, structural, or informational only.
Do not let quoted authority, external polish, or prior wording override the current repo's source-of-truth order.
Working Rules
- Treat
/caret-cheatsheet.mdas the product artifact. - Treat
/notation/as the canonical expansion of that artifact. - Treat
glossary/,examples/,patterns/, andresearch/as downstream support surfaces. - Do not infer canonical meaning from patterns, examples, or research if they conflict with the cheatsheet or notation docs.
- If the cheatsheet changes, review every notation-bearing file in the repo.
Editing Guidance
- Keep the cheatsheet compact.
- Keep notation docs precise, restrained, and implementation-aware.
- Keep this file operational rather than promotional.
- Stronger brand voice is acceptable in outward-facing docs such as
/README.md, pattern docs, and manifesto-style writing. - Do not add new syntax without updating the canonical notation docs and recording the decision.
Interpretation And Safety
- The notation signals intent. It does not grant permission.
- Preserve literal examples inside fenced code blocks.
- Keep trust-boundary guidance explicit.
- Do not silently invent unresolved targets, workers, personas, or skills.
- Prefer exact repo-relative targets in examples when precision matters.
Rebuild Rule
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 · 60 lines · 458 tokens per session scan A becbc64f9c56
caret AGENTS.md is an instructions file published in the GitHub repository disruptionjoe/caret (5 stars, last pushed 5mo ago), licensed MIT. It adds 458 tokens to every session, about $0.0023 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
deer-flow copilot-instructions.md
Copilot instructions for bytedance/deer-flow, covering copilot onboarding instructions for deerflow, 1) repository summary, 2) runtime and toolchain requirements, 3) build/test/lint/run - verified command sequences and a. bootstrap and install.
LeAgent AGENTS.md
Instructions for vixues/LeAgent, covering leagent development guidelines, project overview, architecture, execution topology (one kernel, many ingresses) and surface map (where things live).
sprawling CLAUDE.md
Instructions for 2youg1/sprawling: See AGENTS.md. It is the whole instruction set for this repository — the loop, what to read first, the five steps of one change, the rules a machine holds, and the language and commit conventions.
codex-acp-bridge AGENTS.md
Instructions for normahq/codex-acp-bridge, covering codex-acp-bridge — agents.md, development standards, quality gates (required), logging policy and bridge guardrails.
deckforge AGENTS.md
Instructions for tph-kds/deckforge, covering deckforge agent entry point, code intelligence, read order, default routing and non-negotiable implementation rules.
vant AGENTS.md
AGENTS.md instructions for dhaupin/vant, covering agents.md — vant agent guide, what is vant?, your job, brain router interface and middleware chain.