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 tokencanopy/e2a --skill e2a-doctorgit clone --depth 1 https://github.com/tokencanopy/e2aWrote 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/tokencanopy/e2a/e2a-doctor)<a href="https://agentmods.dev/skills/tokencanopy/e2a/e2a-doctor"><img src="https://agentmods.dev/badge/skills/tokencanopy/e2a/e2a-doctor/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/tokencanopy/e2a/e2a-doctor"><img src="https://agentmods.dev/badge/skills/tokencanopy/e2a/e2a-doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00069 | $0.00827 |
| Opus 5.5 | $0.00028 | $0.00331 |
| Sonnet 5.5 | $0.00014 | $0.00165 |
| Haiku 4.5 | $0.00007 | $0.00083 |
Grade A, and why
e2a-doctor 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 1mo 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnose and repair e2a
Start from the symptom
Identify the failing surface and the smallest safe target: an inbox address, domain,
webhook ID, message ID, time window, or exact error. Do not request message content
unless it is necessary to diagnose the symptom. Inspect the available e2a MCP tools;
use the e2a MCP whoami tool, never the shell command.
Keep diagnosis separate from repair. Begin MCP-first, read-only diagnosis with the existing authorization; do not create a second credential or alter configuration.
Read-only MCP diagnosis
Call whoami first, then load only the symptom's minimum reads from
the diagnostic matrix. Use get_agent or
list_agents only to establish inbox access; read get_protection and
list_pending_messages for holds; use list_suppressions and
list_agent_suppressions for recipient blocks; inspect get_domain and public,
read-only DNS for domain symptoms; inspect get_webhook and
list_webhook_deliveries for a webhook; and call get_message_lifecycle for one
message's observed transitions.
Do not convert a missing tool, account-only scope, 401/403, or unavailable permission
into a pass. Record it as an explicit skipped check, naming the unavailable read and
the scope or authorization needed. Do not call verify_domain, test_webhook,
redeliver_event, or any mutation while diagnosing.
Rank findings
Return a ranked list. Every finding must include {cause, evidence, impact, remediation} and state whether it is a definite configuration failure, authorization
failure, asynchronous pending state, or transient service failure. Rank definite,
high-impact causes above possibilities; keep evidence factual and targeted.
Treat accepted, scheduled, and pending_review as durable outcomes, not delivery
receipts. Do not retry them: a second send can duplicate mail. Report the lifecycle or
hold state, then wait for its next transition or an authorized human decision.
Offer guided repairs
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 75 lines · 69 tokens per session scan A 697e114b8da6
e2a-doctor is a skill published in the GitHub repository tokencanopy/e2a (194 stars, last pushed yesterday), licensed Apache-2.0. It adds 69 tokens to every session and 827 once invoked, about $0.0003 per session on Opus 5.5. 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 skills, from other repositories
functions-development
Build serverless Go or Python functions for Falcon Foundry apps. TRIGGER when user asks to "create a function", "write a serverless function", "build backend logic", runs foundry functions create, or needs help with FDK handler patterns, function testing, or collection integration from functions. Also TRIGGER when…
others-skills
Use when needing Go language development, desktop RPA automation, self-hosted email marketing, Java Spring Cloud scaffolding, SSL/TLS certificate automation, Docker Compose multi-container orchestration, or building a bilingual children's Phaser/Vue game collection. Index of 8 skills: Go, RobotGo, RobotGo-Flow…
resonate-basic-debugging-python
Debug and troubleshoot Resonate applications using the Python SDK v0.7.0 and Resonate Server v0.9.x. Use when investigating stuck workflows, non-deterministic replays, registration errors, async/await mistakes, unexpected retries, or server connectivity issues.
skills
Email API for AI agents. Create inboxes, send/receive email, manage threads and webhooks.
nodejs-core
Debugs native module crashes, optimizes V8 performance, configures node-gyp builds, writes N-API/node-addon-api bindings, and diagnoses libuv event loop issues in Node.js. Use when working with C++ addons, native modules, binding.gyp, node-gyp errors, segfaults, memory leaks in native code, V8…
go-concurrency-patterns
Master Go concurrency with goroutines, channels, sync primitives, and context. Use when building concurrent Go applications, implementing worker pools, or debugging race conditions.