Borrowing it
Nothing to install: this file belongs to shbernal/caniemail-ai-tooling. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/shbernal/caniemail-ai-tooling/main/AGENTS.mdgit clone --depth 1 https://github.com/shbernal/caniemail-ai-toolingWrote 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/instructions/shbernal/caniemail-ai-tooling/agents-md)<a href="https://agentmods.dev/instructions/shbernal/caniemail-ai-tooling/agents-md"><img src="https://agentmods.dev/badge/instructions/shbernal/caniemail-ai-tooling/agents-md/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/instructions/shbernal/caniemail-ai-tooling/agents-md"><img src="https://agentmods.dev/badge/instructions/shbernal/caniemail-ai-tooling/agents-md.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 | $0.05002 | $0.05002 |
| Opus 5.5 | $0.02001 | $0.02001 |
| Sonnet 5.5 | $0.01000 | $0.01000 |
| Haiku 4.5 | $0.00500 | $0.00500 |
Grade A, and why
caniemail-ai-tooling 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 29d 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 — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI agents working in this repo.
What this is
Two surfaces (an agent skill and an MCP server) over one shared core
(core/caniemail-core.mjs) giving an agent access to email client HTML/CSS
compatibility data. See README.md for the full pitch and usage.
core/ the implementation and its tests, the only real source
skill/ SKILL.md, a CLI, and a vendored copy of the core
mcp/ the mcp-server-caniemail npm package, a thin adapter over the core
The shipped core has zero runtime dependencies. Node 24+ and nothing else.
That is a property to preserve, not an accident: it is what lets skill/ run
from a bare checkout with no package.json and no install step.
Released
Both surfaces are live: mcp-server-caniemail on npm and email-compat on
ClawHub. docs/releasing.md has the process for each.
Which version is current is deliberately not written here. git tag and the top
of CHANGELOG.md both answer it, and a number copied into prose is one more
thing a release has to remember to move. This file went two releases describing
the first one.
Publishing is automated. .github/workflows/publish.yml uploads to npm on a
v* tag push and to ClawHub on a published release, and it re-runs the full
suite on the released ref first. A tag does not match CI's branches: [main]
filter, so without that job the released commit would reach both registries with
nothing verified on it. Both halves are idempotent, so a partly-failed release
can be re-run.
Both registries treat a version as permanent. Never delete or re-publish a released version; fix forward with a version bump on whichever surfaces are affected. The two artifacts are independent and their version numbers are not required to move together. Couple them only when a change reaches both.
Breaking changes are welcome
Released constrains what a published version means, not what the next one may do. When the better behaviour is incompatible with the old one, ship the better behaviour: remove the old one and bump the version.
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.
- 29d ago Changed · +9 lines · +141 tokens per session d87d9303011b
- 1mo ago Changed · +19 lines · +326 tokens per session 8315fda5c3e6
- 1mo ago Changed 9eef0e8a4d96
- 2mo ago Changed · +16 lines · +207 tokens per session 684d0cd8ea65
- 2mo ago First seen · 321 lines · 4,328 tokens per session scan A 0e96515dcc59
caniemail-ai-tooling AGENTS.md is an instructions file published in the GitHub repository shbernal/caniemail-ai-tooling (1 stars, last pushed 10d ago), licensed MIT. It adds 5,002 tokens to every session, about $0.0200 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 2026-08-31.
caniemail-ai-tooling AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| caniemail-ai-tooling AGENTS.mdshbernal/caniemail-ai-tooling | Instructions file | 1 | 10d ago | MIT | A | 5,002 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |