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/clabby/tact/agents-mdgit clone --depth 1 https://github.com/clabby/tactWhat 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 | $0.00568 | $0.00568 |
| Opus 5 | $0.00284 | $0.00284 |
| Sonnet 5 | $0.00114 | $0.00114 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
tact 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 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working Agreements
Common Dev Commands
cargo check --all-features: Check compilation.just check-fmt: Check formatting.just fmt: Fix formatting.just clippy: Run clippy.just test: Run tests
Code
- Optimize for the reader. Code should be obvious on the first pass and easy to scan later.
- Prefer explicit data flow, small cohesive modules, descriptive names, and early returns.
- Prefer associated functions when behavior naturally belongs to a type. Use free functions for module-level operations that have no clear owner.
- Import types into scope instead of qualifying their full paths at use sites. Alias imports when names conflict.
- Keep parsing and presentation at the boundary. Core types should not depend on CLI or terminal concerns unless that removes meaningful duplication.
- Keep visibility as narrow as possible. Prefer private items, then
pub(crate); add public APIs only when another crate needs them. - Avoid clever abstractions, hidden control flow, premature generalization, and tiny pass-through helpers.
- Remove meaningful repetition with shared functions or test harnesses, but do not abstract one-line operations merely to be DRY.
- Model distinct states with enums and typed structures instead of loosely related booleans or strings.
- Use typed errors with useful context. Preserve error sources and identify relevant paths or operations.
- Add dependencies only when they make the implementation materially smaller, safer, or clearer.
Secrets
- Secret-owning application types must implement
Zeroizeand zeroize on drop. - Secret wrappers must not implement
Clone,Display, or serialization. TheirDebugoutput must be redacted. - Secret access must be explicit and narrowly scoped. Never include credentials in logs, errors, status output, configuration rendering, or tests.
- Document ownership boundaries when a dependency retains a non-zeroizing copy; do not claim guarantees beyond memory owned by this crate.
Documentation
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 · 51 lines · 568 tokens per session scan A e6a7d57817d6
tact AGENTS.md is an instructions file published in the GitHub repository clabby/tact (89 stars, last pushed 4d ago), licensed Apache-2.0. It adds 568 tokens to every session, about $0.0028 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 2026-08-30.
Other instructions, from other repositories
open-swe AGENTS.md
AGENTS.md instructions for langchain-ai/open-swe, covering agents.md, project, commands, architecture and entrypoints.
open-swe CLAUDE.md
Claude Code instructions for langchain-ai/open-swe, covering claude.md, project, commands, architecture and entrypoints.
LangBot AGENTS.md
Instructions for langbot-app/LangBot, covering agents.md, quick facts, essential commands, where to look and cross-repo sdk work.
awesome-ChatGPT-repositories CLAUDE.md
Claude Code instructions for taishi-i/awesome-ChatGPT-repositories, covering awesome-chatgpt-repositories — claude code guide, repository structure, plugin skill (when installed via /plugin), local standalone command (when repo is cloned) and compact data format (plugins/awesome-chatgpt-search/data/).
dify AGENTS.md
AGENTS.md instructions for langgenius/dify, covering agents.md, repository gotchas and frontend workflow.
dify CLAUDE.md
Claude Code instructions for langgenius/dify, a project described as: Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.