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/evermind-ai/everme/agents-mdgit clone --depth 1 https://github.com/EverMind-AI/EverMeWhat 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 | $0.00938 | $0.00938 |
| Opus 5 | $0.00469 | $0.00469 |
| Sonnet 5 | $0.00188 | $0.00188 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
EverMe 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 3d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Goal (pick one per PR)
- Make CLI better: improve UX, error messages, help text, flags, and output clarity.
- Improve plugin reliability: fix host integration bugs, edge cases, and regressions with tests.
- Improve developer velocity: simplify code paths, reduce complexity, keep behavior explicit.
- Improve quality gates: strengthen tests, packaging checks, and security checks without adding heavy process.
Build & Test
cd cli && make build
cd cli && make test
cd plugins && npm ci
cd plugins && npm test --workspaces --if-present
Pre-PR Checks (match CI gates)
cd cli && go test ./... -count=1cd cli && go vet ./...cd cli && gofmt -l .— must produce no output.cd cli && go mod tidy— must not changego.mod/go.sum.cd plugins && npm cicd plugins && npm test --workspaces --if-presentcd plugins && npm audit --audit-level=moderate- Verify no generated artifacts are present:
cli/_output,cli/dist,plugins/node_modules,*.tar.gz,*.zip,.env*.
Commit & PR
- Conventional Commits in English:
feat:,fix:,docs:,test:,refactor:,chore:,ci:. - PR title should use the same format.
- Fill
.github/pull_request_template.mdcompletely. - Never commit secrets, tokens, private URLs, internal logs, or generated build artifacts.
Source Layout
| Path | What it does |
|---|---|
cli/cmd/ |
Cobra command surface for auth, plugin install, import, and doctor. |
cli/internal/client/ |
EverMe gateway HTTP client and envelope handling. |
cli/internal/output/ |
CLI output contract, exit codes, and redaction. |
cli/internal/plugin/ |
Host config writers for Codex, Claude Code, Claude Desktop, Cursor, OpenClaw, Hermes, and MCP. |
cli/internal/importer/ |
Cold-start memory import scanning and upload flow. |
plugins/agent-sdk/ |
Shared JavaScript client and host-agnostic helpers. |
plugins/memory-mcp/ |
Generic MCP server for memory recall and writes. |
plugins/claude-code/ |
Claude Code native plugin: hooks, slash commands, skill, and MCP server. |
plugins/openclaw/ |
OpenClaw ContextEngine plugin. |
plugins/cli/ |
npm wrapper that downloads and runs the platform-native evercli binary. |
plugins/everme/ |
Codex marketplace plugin and memory skill. |
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.
- 3d ago First seen · 91 lines · 938 tokens per session scan A 825bcb5e9c01
EverMe AGENTS.md is an instructions file published in the GitHub repository EverMind-AI/EverMe (57 stars, last pushed 5d ago), licensed Apache-2.0. It adds 938 tokens to every session, about $0.0047 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 2026-08-30.
Other instructions, from other repositories
Dragon-Brain CLAUDE.md
Instructions for iikarus/Dragon-Brain, covering dragon brain — claude.md, the harness, audit remediation (april–may 2026, complete 2026-05-09), the lie this audit closed and the contract that matters now.
cargo-skills AGENTS.md
Instructions for getcargohq/cargo-skills, covering cargo skills — agent guide and working in this repo.
vestige CLAUDE.md
Claude Code instructions for samvallad33/vestige, covering vestige agent guidance, project shape, working rules, common checks and documentation.
mcp-server GEMINI.md
Instructions for contextstream/mcp-server: Persistent project memory for AI coding agents. Connect via hosted MCP.
cosmos-mcp CLAUDE.md
Instructions for teampolarity/cosmos-mcp, covering cosmos-mcp, layout, tools (authoritative list in src/tools/index.ts), cli subcommands and imessage is the headline source.
memoir CLAUDE.md
Instructions for camgitt/memoir, covering memoir — persistent memory for ai coding tools, project, what it does, architecture and key files.