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/extend-hq/extend-cli/agents-mdgit clone --depth 1 https://github.com/extend-hq/extend-cliWhat 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 | $0.00582 | $0.00582 |
| Opus 5 | $0.00291 | $0.00291 |
| Sonnet 5 | $0.00116 | $0.00116 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
extend-cli 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 2d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
extend is a Go CLI for the Extend document AI platform. Entrypoint:
cmd/extend. Every command is built on the Extend Go SDK
(github.com/extend-hq/extend-go-sdk) wired through internal/extendx.
Build & test
go build ./...
go test ./... # unit tests; no network, fast
go vet ./...
gofmt -l cmd internal # must print nothing
Integration tests are a separate module under test/integration (black-box:
they build and exec the binary). They need EXTEND_BASE_URL and
EXTEND_API_KEY and skip silently without them; run-creating ops that spend
credits are gated behind EXTEND_TEST_RUN_OPS=1:
cd test/integration && go test ./...
Skill evals (drive real Claude Code / Codex harnesses) are another module
under evals/runner; see evals/README.md.
Layout
cmd/extend— main entrypoint.internal/cli— every command, group, and help topic; the typed CommandDoc tree is the source of truth (seeinternal/cli/AGENTS.md).internal/extendx— SDK client construction, run polling/wait, file I/O.internal/oauth: browser login (PKCE flow, loopback redirect, token storage in the keychain with file fallback, silent refresh).internal/output,internal/iostreams— rendering and stream handling.evals/— skill-eval harness (seeevals/AGENTS.md).
Conventions
- A command's
--helpand the generatedSKILL.mdare projections of the CommandDoc tree — change the doc, never hand-edit generated skill output. - Never commit secrets or API keys.
Keep the scoped AGENTS.md files current
Subtrees with their own contracts carry a local AGENTS.md that is the
source of truth for their area. When a change touches that area, update its
AGENTS.md in the same change — drift is a defect, not a follow-up:
internal/cli/AGENTS.md— the CommandDoc documentation contract: how every command, group, and help topic is declared, the required fields per node kind, and the validators that enforce them.evals/AGENTS.md— the skill-eval authoring contract: the case schema and Path A/B split, expectation types, stub modes and per-command help, and ID-fabrication patterns.
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.
- 2d ago First seen · 55 lines · 582 tokens per session scan A c3a5184615cd
extend-cli AGENTS.md is an instructions file published in the GitHub repository extend-hq/extend-cli (49 stars, last pushed 5d ago), licensed MIT. It adds 582 tokens to every session, about $0.0029 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
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.