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 skills add ychampion/cskill-agents --skill session-memory-mailbox-exclusiongit clone --depth 1 https://github.com/ychampion/cskill-agentsWrote 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/skills/ychampion/cskill-agents/session-memory-mailbox-exclusion)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/session-memory-mailbox-exclusion"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/session-memory-mailbox-exclusion/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ychampion/cskill-agents/session-memory-mailbox-exclusion"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/session-memory-mailbox-exclusion.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00025 | $0.00382 |
| Opus 5 | $0.00013 | $0.00191 |
| Sonnet 5 | $0.00005 | $0.00076 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
session-memory-mailbox-exclusion 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 8d 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.
What it actually says
SKILL: Session Memory Mailbox Exclusion
Domain: multi-agent
Trigger: Apply when a background or forked agent shares team context with a leader thread and must not consume mailbox messages intended for the leader.
Source Pattern: Distilled from reviewed multi-agent coordination and child-runtime patterns.
Core Method
Treat mailbox-draining attachments as ownership-sensitive, not universally thread-safe. When a background fork shares the same team context as the lead agent, exclude the mailbox attachment path for that fork so it cannot mark leader messages as read and silently steal them from the permanent conversation stream. Keep the exclusion narrow and source-based so the main thread and legitimate teammate consumers still receive mailbox attachments normally.
Key Rules
- Identify fork classes that share mailbox state with the leader and exclude them from the mailbox drain path.
- Keep the exclusion focused on the mailbox attachment only; other safe shared attachments should continue to run.
- Prefer a source or role check that is stable at attachment time so the guard cannot drift with transient runtime conditions.
- Document why the exclusion exists: the failure mode is message theft, not just redundant work.
Example Application
If a session-memory extractor runs as a background fork against the same team context as the lead agent, skip its teammate mailbox attachment. The leader still receives teammate DMs as durable conversation turns, while the background worker avoids consuming them as ephemeral side attachments.
Anti-Patterns (What NOT to do)
- Do not let every fork drain the shared mailbox; one background consumer can mark the leader's unread messages as handled.
- Do not disable all shared attachments for background forks just to solve mailbox theft; keep the guard scoped to the unsafe mailbox path.
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.
- 8d ago First seen · 28 lines · 25 tokens per session scan A a87f9c92cb3f
session-memory-mailbox-exclusion is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 25 tokens to every session and 382 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
grape
Use Grape MCP for Codex context continuity in coding repositories. Use when a task needs repeated-turn context, omitted context restore, stale-context checks, invalidation checks, or safe continuity across branch and dirty-worktree changes.
review
Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.
work
Execute an approved wish plan — orchestrate subagents per task group with fix loops, validation, and review handoff.
brainstorm
Explore ambiguous or early-stage ideas interactively — tracks wish-readiness and crystallizes into a design for wish.
genie
Entry point for Genie operations — routes bug reports, questions, and operational commands, resumes existing lifecycle state, and orchestrates work that needs durable planning or coordination. Other ordinary requests bypass the lifecycle with a one-line notice unless the user asks for Genie.
wish
Convert an idea into a structured wish plan with scope, acceptance criteria, and execution groups for work.