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/spxrogers/agentsync/agents-mdgit clone --depth 1 https://github.com/spxrogers/agentsyncWhat 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 | $0.06205 | $0.06205 |
| Opus 5 | $0.03102 | $0.03102 |
| Sonnet 5 | $0.01241 | $0.01241 |
| Haiku 4.5 | $0.00620 | $0.00620 |
Grade A, and why
agentsync 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- agentsync CLAUDE.md — 98% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Managed by agentsync — do not edit
AGENTS.mddirectly. To change it, edit.agentsync/memory/AGENTS.md(or the relevant.agentsync/memory/fragments/*.mdfragment) and runagentsync apply. Direct edits here are reported as drift and overwritten on the next apply.
CLAUDE.md
Project memory for Claude Code / agent sessions working on agentsync.
What this is
agentsync is a single-machine Go CLI that centrally manages AI coding-agent
configurations (31 agents: nine deep adapters — Claude Code, OpenCode, Codex,
Cursor, Gemini CLI, Continue, Windsurf, Roo Code, Cline — plus a 22-agent generic
"breadth tier" for memory + MCP + skills). The
user keeps a canonical config in ~/.agentsync/ (small TOML + markdown,
committable to a dotfiles repo); agentsync apply renders it into each agent's
native config. It's bidirectional: native edits are detected as drift and merged
back via reconcile/import. Secrets are ${secret:…}/${env:…} references
resolved at apply time from an age-encrypted vault.
Read the docs before large changes:
docs/concepts.md— the three-state model + every term.docs/architecture.md— pipelines, drift classifier, secret invariants, package layering.docs/components.md— package-by-package map.docs/capability-matrix.md— per-agent support.docs/superpowers/specs/2026-05-04-agentsync-design.md— the authoritative v1.0 design. Note: a few items in its §"CLI surface" were aspirational and not wired in v1.0 (apply --strict/--force/--agentflags, anagentsync skillcommand) — trust the code over the spec on the CLI surface. Note the last of those has since SHIPPED: F5 addedskill listalongsidesubagent/command/hook/lsp list.
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 · 382 lines · 6,205 tokens per session scan A aa0c7e15f9d5
agentsync AGENTS.md is an instructions file published in the GitHub repository spxrogers/agentsync (9 stars, last pushed 1mo ago), licensed MIT. It adds 6,205 tokens to every session, about $0.0310 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
mcp-server-manager CLAUDE.md
Instructions for vlazic/mcp-server-manager, covering claude.md, project overview, development guidelines, important development notes and core commands.
azure-sdk-for-go go-code.instructions.md
Instructions for Azure/azure-sdk-for-go: All code should follow the guidelines from the Azure Go SDK Guidelines. This document is a summary of the most important guidelines to follow when contributing to the Azure Go SDK.
chatgpt-cli CLAUDE.md
Instructions for kardolus/chatgpt-cli, covering chatgpt-cli — release runbook, prerequisites, 1. cut the release, 2. publish the github release + binaries and 3. update the homebrew tap.
coder CLAUDE.md
Claude Code instructions for coder/coder, a project described as: Secure environments for developers and their agents.
Sighthound AGENTS.md
Instructions for Corgea/Sighthound, covering claude, commands, python / django test naming and agent skill.
openings-mcp AGENTS.md
Instructions for amikai/openings-mcp, a project described as: 💼 One MCP server to search job boards and company career sites.