Agent Mail
Advisory file reservations and messaging to coordinate multiple agents writing one repo
Test report
- Verdict
- Works with setup
- Score
- Tested
- Jul 21, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 6c2b938
⚠ The author changed this skill after we tested it. The verdict below describes the version we ran on Jul 21, 2026; it's queued for a re-test.
Located SKILL.md at skills/agent-mail/SKILL.md (mirrored in skills-codex/ and images/gemini/skills/). Frontmatter parses with name+description; all three referenced files (references/TOOLS.md, WORKFLOWS.md, RECOVERY.md) returned HTTP 200; paths are relative with no hardcoded machine paths. No security smells (no curl|sh, base64, or exfiltration); it describes a destructive `clear-and-reset-everything` and a git pre-commit guard but gates both behind explicit per-operation caller authorization. TRIGGER: I judged 5 phrasings — SHOULD: "coordinate two agents editing the same repo so they don't clobber files", "reserve src/auth/** while I refactor so the other writer stays off it", "set up file reservations for our multi-agent session"; should NOT: "email my client about the invoice", "reserve a conference room for the team meeting" — all 5 decided correctly (the description clearly scopes it to agent-to-agent coordination, not real mail). OUTPUT unmeasurable: the skill is a thin adapter whose every action requires the Agent Mail MCP tools or an `am` CLI, and `which am` returned not found with no MCP present; I could only fabricate ids/reservations, which would not honestly measure the skill. DOCS solid and refreshingly non-overselling (explicit "does not do" boundary, named failure modes), docked 1 point because nothing in the skill or its references tells you how to obtain/install the backend the whole skill depends on. Note: frontmatter sets user-invocable:false (meant to be consumed by the agent-native skill), so a human won't invoke it directly.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 5/10
- Docs & honesty 4/5
What Agent Mail does
Agent Mail is a Claude/Codex skill that acts as an adapter over an external "Agent Mail" backend (MCP tools or an `am` CLI) for coordinating multiple agents writing to the same repository. It registers agent identities, sends threaded messages/acknowledgements, and places advisory, TTL-bounded file reservations so cooperating writers avoid clobbering each other's paths. It triggers on multi-agent coordination requests like "coordinate writers" or "reserve files".
How to install Agent Mail
git clone --depth 1 https://github.com/boshu2/agentops.git /tmp/agent-mail-src
mkdir -p ~/.claude/skills
cp -R /tmp/agent-mail-src/skills/agent-mail ~/.claude/skills/agent-mail
# REQUIRES an external "Agent Mail" backend that is NOT installed by the copy above:
# either the Agent Mail MCP tools (ensure_project, register_agent, send_message,
# file_reservation_paths, ...) registered in your client, OR a self-describing `am` CLI
# on PATH (discover syntax via `am mail --help`, `am file_reservations --help`).
# Neither ships in this skill folder; the skill only orchestrates them. Without one of
# them present the skill's own "Adapter unavailable" branch says to stop.
# `am`/agentops CLI appears to live in the repo's cli/ (Go); building/running it plus its
# datastore is a separate setup step not covered by the skill files.
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Agent Mail
-
/agent-mailAdvisory file reservations and messaging to coordinate multiple agents writing one repo
It also activates on plain-language prompts like these:
-
Coordinate these two agents using Agent Mail -
Set up a lock so agents don't collide on this file -
Hand off this task to another agent via inbox
Frequently asked questions
- Is the Agent Mail skill free?
- Yes. The skill itself is free from boshu2/agentops. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Agent Mail work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Works with setup. Located SKILL.md at skills/agent-mail/SKILL.md (mirrored in skills-codex/ and images/gemini/skills/). Frontmatter parses with name+description; all three referenced files (references/TOOLS.md, WORKFLOWS.md, RECOVERY.md) returned HTTP 200; paths are relative with no hardcoded machine paths. No security smells (no curl|sh, base64, or exfiltration); it describes a destructive `clear-and-reset-everything` and a git pre-commit guard but gates both behind explicit per-operation caller authorization. TRIGGER: I judged 5 phrasings — SHOULD: "coordinate two agents editing the same repo so they don't clobber files", "reserve src/auth/** while I refactor so the other writer stays off it", "set up file reservations for our multi-agent session"; should NOT: "email my client about the invoice", "reserve a conference room for the team meeting" — all 5 decided correctly (the description clearly scopes it to agent-to-agent coordination, not real mail). OUTPUT unmeasurable: the skill is a thin adapter whose every action requires the Agent Mail MCP tools or an `am` CLI, and `which am` returned not found with no MCP present; I could only fabricate ids/reservations, which would not honestly measure the skill. DOCS solid and refreshingly non-overselling (explicit "does not do" boundary, named failure modes), docked 1 point because nothing in the skill or its references tells you how to obtain/install the backend the whole skill depends on. Note: frontmatter sets user-invocable:false (meant to be consumed by the agent-native skill), so a human won't invoke it directly.
- What is the Agent Mail SkillProof Score?
- 7.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 4/5.
- How do I install Agent Mail?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Agent Mail with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.